Search

This project explores theories of play as they pertain to video games, Indigeneity, and queerness. Recent research into Indigenous video games tends to focus on the developer side, but an indigenized theory of play is necessary to account for movements through colonized artforms and spaces. Introducing identity back into play can help both illuminate how one plays themselves onto a game and how to critique and resist gaming normativities by altering or disengaging gameplay. This project considers games from several genres, geographies, cultures, and colonial engagements, as well as sovereign games developed from Indigenous perspectives to read back onto colonization.

GIS Day was a small, local offering dependent on individual institutions, until the COVID-19 pandemic prompted a wealth of online events. After 3 years of successive development, 2022 saw this event span multiple days and reach beyond Western University to institutions across Canada. The planning process, events, and outcome are here described as inspiration for future events by interested parties, and to acknowledge the work of those involved while simultaneously promoting the current work in GIS being undertaken and potential future directions for event organizers.

Contemporary scientific research is a distributed, collaborative endeavor, carried out by teams of researchers, regulatory institutions, funding agencies, commercial partners, and scientific bodies, all interacting with each other and facing different incentives. To maintain scientific rigor, statistical methods should acknowledge this state of affairs. To this end, we study hypothesis testing when there is an agent (e.g., a researcher or a pharmaceutical company) with a private prior about an unknown parameter and a principal (e.g., a policymaker or regulator) who wishes to make decisions based on the parameter value. The agent chooses whether to run a statistical trial based on their private prior and then the result of the trial is used by the principal to reach a decision. We show how the principal can conduct statistical inference that leverages the information that is revealed by an agent's strategic behavior -- their choice to run a trial or not. In particular, we show how the principal can design a policy to elucidate partial information about the agent's private prior beliefs and use this to control the posterior probability of the null. One implication is a simple guideline for the choice of significance threshold in clinical trials: the type-I error level should be set to be strictly less than the cost of the trial divided by the firm's profit if the trial is successful.

We present a method for solving general nonconvex-strongly-convex bilevel optimization problems. Our method -- the \emph{Restarted Accelerated HyperGradient Descent} (\texttt{RAHGD}) method -- finds an $\epsilon$-first-order stationary point of the objective with $\tilde{\mathcal{O}}(\kappa^{3.25}\epsilon^{-1.75})$ oracle complexity, where $\kappa$ is the condition number of the lower-level objective and $\epsilon$ is the desired accuracy. We also propose a perturbed variant of \texttt{RAHGD} for finding an $\big(\epsilon,\mathcal{O}(\kappa^{2.5}\sqrt{\epsilon}\,)\big)$-second-order stationary point within the same order of oracle complexity. Our results achieve the best-known theoretical guarantees for finding stationary points in bilevel optimization and also improve upon the existing upper complexity bound for finding second-order stationary points in nonconvex-strongly-concave minimax optimization problems, setting a new state-of-the-art benchmark. Empirical studies are conducted to validate the theoretical results in this paper.

Numerous applications in machine learning and data analytics can be formulated as equilibrium computation over Riemannian manifolds. Despite the extensive investigation of their Euclidean counterparts, the performance of Riemannian gradient-based algorithms remain opaque and poorly understood. We revisit the original scheme of Riemannian gradient descent (RGD) and analyze it under a geodesic monotonicity assumption, which includes the well-studied geodesically convex-concave min-max optimization problem as a special case. Our main contribution is to show that, despite the phenomenon of distance distortion, the RGD scheme, with a step size that is agnostic to the manifold's curvature, achieves a curvature-independent and linear last-iterate convergence rate in the geodesically strongly monotone setting. To the best of our knowledge, the possibility of curvature-independent rates and/or last-iterate convergence in the Riemannian setting has not been considered before.

For content recommender systems such as TikTok and YouTube, the platform's decision algorithm shapes the incentives of content producers, including how much effort the content producers invest in the quality of their content. Many platforms employ online learning, which creates intertemporal incentives, since content produced today affects recommendations of future content. In this paper, we study the incentives arising from online learning, analyzing the quality of content produced at a Nash equilibrium. We show that classical online learning algorithms, such as Hedge and EXP3, unfortunately incentivize producers to create low-quality content. In particular, the quality of content is upper bounded in terms of the learning rate and approaches zero for typical learning rate schedules. Motivated by this negative result, we design a different learning algorithm -- based on punishing producers who create low-quality content -- that correctly incentivizes producers to create high-quality content. At a conceptual level, our work illustrates the unintended impact that a platform's learning algorithm can have on content quality and opens the door towards designing platform learning algorithms that incentivize the creation of high-quality content.

Large Language Models (LLMs) and other large foundation models have achieved noteworthy success, but their size exacerbates existing resource consumption and latency challenges. In particular, the large-scale deployment of these models is hindered by the significant resource requirements during inference. In this paper, we study two approaches for mitigating these challenges: employing a cache to store previous queries and learning a model multiplexer to choose from an ensemble of models for query processing. Theoretically, we provide an optimal algorithm for jointly optimizing both approaches to reduce the inference cost in both offline and online tabular settings. By combining a caching algorithm, namely Greedy Dual Size with Frequency (GDSF) or Least Expected Cost (LEC), with a model multiplexer, we achieve optimal rates in both offline and online settings. Empirically, simulations show that the combination of our caching and model multiplexing algorithms greatly improves over the baselines, with up to $50\times$ improvement over the baseline when the ratio between the maximum cost and minimum cost is $100$. Experiments on real datasets show a $4.3\times$ improvement in FLOPs over the baseline when the ratio for FLOPs is $10$, and a $1.8\times$ improvement in latency when the ratio for average latency is $1.85$.

Reinforcement learning from human feedback (RLHF) has emerged as a reliable approach to aligning large language models (LLMs) to human preferences. Among the plethora of RLHF techniques, proximal policy optimization (PPO) is of the most widely used methods. Despite its popularity, however, PPO may suffer from mode collapse, instability, and poor sample efficiency. We show that these issues can be alleviated by a novel algorithm that we refer to as Advantage-Induced Policy Alignment (APA), which leverages a squared error loss function based on the estimated advantages. We demonstrate empirically that APA consistently outperforms PPO in language tasks by a large margin, when a separate reward model is employed as the evaluator. In addition, compared with PPO, APA offers a more stable form of control over the deviation from the model's initial policy, ensuring that the model improves its performance without collapsing to deterministic output. In addition to empirical results, we also provide a theoretical justification supporting the design of our loss function.

Self-training is an important technique for solving semi-supervised learning problems. It leverages unlabeled data by generating pseudo-labels and combining them with a limited labeled dataset for training. The effectiveness of self-training heavily relies on the accuracy of these pseudo-labels. In this paper, we introduce doubly robust self-training, a novel semi-supervised algorithm that provably balances between two extremes. When the pseudo-labels are entirely incorrect, our method reduces to a training process solely using labeled data. Conversely, when the pseudo-labels are completely accurate, our method transforms into a training process utilizing all pseudo-labeled data and labeled data, thus increasing the effective sample size. Through empirical evaluations on both the ImageNet dataset for image classification and the nuScenes autonomous driving dataset for 3D object detection, we demonstrate the superiority of the doubly robust loss over the standard self-training baseline.

From the social sciences to machine learning, it has been well documented that metrics to be optimized are not always aligned with social welfare. In healthcare, Dranove et al. [12] showed that publishing surgery mortality metrics actually harmed the welfare of sicker patients by increasing provider selection behavior. Using a principal-agent model, we directly study the incentive misalignments that arise from such average treated outcome metrics, and show that the incentives driving treatment decisions would align with maximizing total patient welfare if the metrics (i) accounted for counterfactual untreated outcomes and (ii) considered total welfare instead of average welfare among treated patients. Operationalizing this, we show how counterfactual metrics can be modified to satisfy desirable properties when used for ranking. Extending to realistic settings when the providers observe more about patients than the regulatory agencies do, we bound the decay in performance by the degree of information asymmetry between the principal and the agent. In doing so, our model connects principal-agent information asymmetry with unobserved heterogeneity in causal inference.

Adaptivity is an important yet under-studied property in modern optimization theory. The gap between the state-of-the-art theory and the current practice is striking in that algorithms with desirable theoretical guarantees typically involve drastically different settings of hyperparameters, such as step-size schemes and batch sizes, in different regimes. Despite the appealing theoretical results, such divisive strategies provide little, if any, insight to practitioners to select algorithms that work broadly without tweaking the hyperparameters. In this work, blending the "geometrization" technique introduced by Lei & Jordan 2016 and the \texttt{SARAH} algorithm of Nguyen et al., 2017, we propose the Geometrized \texttt{SARAH} algorithm for non-convex finite-sum and stochastic optimization. Our algorithm is proved to achieve adaptivity to both the magnitude of the target accuracy and the Polyak-��ojasiewicz (PL) constant if present. In addition, it achieves the best-available convergence rate for non-PL objectives simultaneously while outperforming existing algorithms for PL objectives., 11 pages, 4 Figures, 20 pages Appendix

We study a heterogeneous agent macroeconomic model with an infinite number of households and firms competing in a labor market. Each household earns income and engages in consumption at each time step while aiming to maximize a concave utility subject to the underlying market conditions. The households aim to find the optimal saving strategy that maximizes their discounted cumulative utility given the market condition, while the firms determine the market conditions through maximizing corporate profit based on the household population behavior. The model captures a wide range of applications in macroeconomic studies, and we propose a data-driven reinforcement learning framework that finds the regularized competitive equilibrium of the model. The proposed algorithm enjoys theoretical guarantees in converging to the equilibrium of the market at a sub-linear rate., 44 pages

We provide a unifying framework for the design and analysis of multi-calibrated and moment-multi-calibrated predictors. Placing the multi-calibration problem in the general setting of \emph{multi-objective learning} -- where learning guarantees must hold simultaneously over a set of distributions and loss functions -- we exploit connections to game dynamics to obtain state-of-the-art guarantees for a diverse set of multi-calibration learning problems. In addition to shedding light on existing multi-calibration guarantees, and greatly simplifying their analysis, our approach yields a $1/\epsilon^2$ improvement in the number of oracle calls compared to the state-of-the-art algorithm of Jung et al. 2021 for learning deterministic moment-calibrated predictors and an exponential improvement in $k$ compared to the state-of-the-art algorithm of Gopalan et al. 2022 for learning a $k$-class multi-calibrated predictor. Beyond multi-calibration, we use these game dynamics to address existing and emerging considerations in the study of group fairness and multi-distribution learning., Comment: 25 pages. Authors are ordered alphabetically

We introduce prediction-powered inference $\unicode{x2013}$ a framework for performing valid statistical inference when an experimental data set is supplemented with predictions from a machine-learning system. Our framework yields provably valid conclusions without making any assumptions on the machine-learning algorithm that supplies the predictions. Higher accuracy of the predictions translates to smaller confidence intervals, permitting more powerful inference. Prediction-powered inference yields simple algorithms for computing valid confidence intervals for statistical objects such as means, quantiles, and linear and logistic regression coefficients. We demonstrate the benefits of prediction-powered inference with data sets from proteomics, genomics, electronic voting, remote sensing, census analysis, and ecology., Code is available at https://github.com/aangelopoulos/prediction-powered-inference

Clustering clients with similar objectives and learning a model per cluster is an intuitive and interpretable approach to personalization in federated learning. However, doing so with provable and optimal guarantees has remained an open challenge. In this work, we formalize personalized federated learning as a stochastic optimization problem where the stochastic gradients on a client may correspond to one of $K$ distributions. In such a setting, we show that using i) a simple thresholding-based clustering algorithm, and ii) local client gradients obtains optimal convergence guarantees. In fact, our rates asymptotically match those obtained if we knew the true underlying clustering of the clients. Furthermore, our algorithms are provably robust in the Byzantine setting where some fraction of the gradients are corrupted.

We study the problem of online learning in a two-player decentralized cooperative Stackelberg game. In each round, the leader first takes an action, followed by the follower who takes their action after observing the leader's move. The goal of the leader is to learn to minimize the cumulative regret based on the history of interactions. Differing from the traditional formulation of repeated Stackelberg games, we assume the follower is omniscient, with full knowledge of the true reward, and that they always best-respond to the leader's actions. We analyze the sample complexity of regret minimization in this repeated Stackelberg game. We show that depending on the reward structure, the existence of the omniscient follower may change the sample complexity drastically, from constant to exponential, even for linear cooperative Stackelberg games. This poses unique challenges for the learning process of the leader and the subsequent regret analysis.

The causal revolution has spurred interest in understanding complex relationships in various fields. Most existing methods aim to discover causal relationships among all variables in a large-scale complex graph. However, in practice, only a small number of variables in the graph are relevant for the outcomes of interest. As a result, causal estimation with the full causal graph -- especially given limited data -- could lead to many falsely discovered, spurious variables that may be highly correlated with but have no causal impact on the target outcome. In this paper, we propose to learn a class of necessary and sufficient causal graphs (NSCG) that only contains causally relevant variables for an outcome of interest, which we term causal features. The key idea is to utilize probabilities of causation to systematically evaluate the importance of features in the causal graph, allowing us to identify a subgraph that is relevant to the outcome of interest. To learn NSCG from data, we develop a score-based necessary and sufficient causal structural learning (NSCSL) algorithm, by establishing theoretical relationships between probabilities of causation and causal effects of features. Across empirical studies of simulated and real data, we show that the proposed NSCSL algorithm outperforms existing algorithms and can reveal important yeast genes for target heritable traits of interest.

One can typically form a local robustness metric for a particular problem quite directly, for Markov chain Monte Carlo applications as well as optimization problems such as variational Bayes. However, we argue that simply forming a local robustness metric is not enough: the hard work is showing that it is useful. Computability, interpretability, and the ability of a local robustness metric to extrapolate well, are more important -- and often more difficult to establish -- than mere computation of derivatives., Comment: Rejoinder for the discussion article "Evaluating Sensitivity to the Stick-Breaking Prior in Bayesian Nonparametrics'' in Bayesian Analysis

As the scale of machine learning models increases, trends such as scaling laws anticipate consistent downstream improvements in predictive accuracy. However, these trends take the perspective of a single model-provider in isolation, while in reality providers often compete with each other for users. In this work, we demonstrate that competition can fundamentally alter the behavior of these scaling trends, even causing overall predictive accuracy across users to be non-monotonic or decreasing with scale. We define a model of competition for classification tasks, and use data representations as a lens for studying the impact of increases in scale. We find many settings where improving data representation quality (as measured by Bayes risk) decreases the overall predictive accuracy across users (i.e., social welfare) for a marketplace of competing model-providers. Our examples range from closed-form formulas in simple settings to simulations with pretrained representations on CIFAR-10. At a conceptual level, our work suggests that favorable scaling trends for individual model-providers need not translate to downstream improvements in social welfare in marketplaces with multiple model providers.

Sleep-wake disturbance is a significant complaint in women receiving chemotherapy for breast cancer. However, sleep problems often go unrecognised during active cancer treatment. If left untreated, cancer-related sleep disturbance may lead to worse psychiatric and physical consequences that can continue well beyond cancer treatment completion. This work contributes to the understanding of sleep-wake disturbance during chemotherapy and presents innovative approaches in targeting poor sleep and daytime impairment during this period. Results generally support the utility for disseminating accessible, evidence-based interventions early in the cancer process.

The creator economy has revolutionized the way individuals can profit through online platforms. In this paper, we initiate the study of online learning in the creator economy by modeling the creator economy as a three-party game between the users, platform, and content creators, with the platform interacting with the content creator under a principal-agent model through contracts to encourage better content. Additionally, the platform interacts with the users to recommend new content, receive an evaluation, and ultimately profit from the content, which can be modeled as a recommender system. Our study aims to explore how the platform can jointly optimize the contract and recommender system to maximize the utility in an online learning fashion. We primarily analyze and compare two families of contracts: return-based contracts and feature-based contracts. Return-based contracts pay the content creator a fraction of the reward the platform gains. In contrast, feature-based contracts pay the content creator based on the quality or features of the content, regardless of the reward the platform receives. We show that under smoothness assumptions, the joint optimization of return-based contracts and recommendation policy provides a regret $\Theta(T^{2/3})$. For the feature-based contract, we introduce a definition of intrinsic dimension $d$ to characterize the hardness of learning the contract and provide an upper bound on the regret $\mathcal{O}(T^{(d+1)/(d+2)})$. The upper bound is tight for the linear family.

Conformal prediction is emerging as a popular paradigm for providing rigorous uncertainty quantification in machine learning since it can be easily applied as a post-processing step to already trained models. In this paper, we extend conformal prediction to the federated learning setting. The main challenge we face is data heterogeneity across the clients - this violates the fundamental tenet of exchangeability required for conformal prediction. We propose a weaker notion of partial exchangeability, better suited to the FL setting, and use it to develop the Federated Conformal Prediction (FCP) framework. We show FCP enjoys rigorous theoretical guarantees and excellent empirical performance on several computer vision and medical imaging datasets. Our results demonstrate a practical approach to incorporating meaningful uncertainty quantification in distributed and heterogeneous environments. We provide code used in our experiments https://github.com/clu5/federated-conformal., Comment: 23 pages, 18 figures, accepted to International Conference on Machine Learning (ICML 2023)

We provide a theoretical framework for Reinforcement Learning with Human Feedback (RLHF). Our analysis shows that when the true reward function is linear, the widely used maximum likelihood estimator (MLE) converges under both the Bradley-Terry-Luce (BTL) model and the Plackett-Luce (PL) model. However, we show that when training a policy based on the learned reward model, MLE fails while a pessimistic MLE provides policies with improved performance under certain coverage assumptions. Additionally, we demonstrate that under the PL model, the true MLE and an alternative MLE that splits the $K$-wise comparison into pairwise comparisons both converge. Moreover, the true MLE is asymptotically more efficient. Our results validate the empirical success of existing RLHF algorithms in InstructGPT and provide new insights for algorithm design. Furthermore, our results unify the problem of RLHF and max-entropy Inverse Reinforcement Learning (IRL), and provide the first sample complexity bound for max-entropy IRL.

ImportanceSARS-CoV-2 infection can result in ongoing, relapsing, or new symptoms or other health effects after the acute phase of infection; termed post-acute sequelae of SARS-CoV-2 infection (PASC), or long COVID. The characteristics, prevalence, trajectory and mechanisms of PASC are ill-defined. The objectives of the Researching COVID to Enhance Recovery (RECOVER) Multi-site Observational Study of PASC in Adults (RECOVER-Adult) are to: (1) characterize PASC prevalence; (2) characterize the symptoms, organ dysfunction, natural history, and distinct phenotypes of PASC; (3) identify demographic, social and clinical risk factors for PASC onset and recovery; and (4) define the biological mechanisms underlying PASC pathogenesis.MethodsRECOVER-Adult is a combined prospective/retrospective cohort currently planned to enroll 14,880 adults aged ≥18 years. Eligible participants either must meet WHO criteria for suspected, probable, or confirmed infection; or must have evidence of no prior infection. Recruitment occurs at 86 sites in 33 U.S. states, Washington, DC and Puerto Rico, via facility- and community-based outreach. Participants complete quarterly questionnaires about symptoms, social determinants, vaccination status, and interim SARS-CoV-2 infections. In addition, participants contribute biospecimens and undergo physical and laboratory examinations at approximately 0, 90 and 180 days from infection or negative test date, and yearly thereafter. Some participants undergo additional testing based on specific criteria or random sampling. Patient representatives provide input on all study processes. The primary study outcome is onset of PASC, measured by signs and symptoms. A paradigm for identifying PASC cases will be defined and updated using supervised and unsupervised learning approaches with cross-validation. Logistic regression and proportional hazards regression will be conducted to investigate associations between risk factors, onset, and resolution of PASC symptoms.DiscussionRECOVER-Adult is the first national, prospective, longitudinal cohort of PASC among US adults. Results of this study are intended to inform public health, spur clinical trials, and expand treatment options.RegistrationNCT05172024.

We study the complexity of optimizing nonsmooth nonconvex Lipschitz functions by producing $(\delta,\epsilon)$-stationary points. Several recent works have presented randomized algorithms that produce such points using $\tilde O(\delta^{-1}\epsilon^{-3})$ first-order oracle calls, independent of the dimension $d$. It has been an open problem as to whether a similar result can be obtained via a deterministic algorithm. We resolve this open problem, showing that randomization is necessary to obtain a dimension-free rate. In particular, we prove a lower bound of $\Omega(d)$ for any deterministic algorithm. Moreover, we show that unlike smooth or convex optimization, access to function values is required for any deterministic algorithm to halt within any finite time. On the other hand, we prove that if the function is even slightly smooth, then the dimension-free rate of $\tilde O(\delta^{-1}\epsilon^{-3})$ can be obtained by a deterministic algorithm with merely a logarithmic dependence on the smoothness parameter. Motivated by these findings, we turn to study the complexity of deterministically smoothing Lipschitz functions. Though there are efficient black-box randomized smoothings, we start by showing that no such deterministic procedure can smooth functions in a meaningful manner, resolving an open question. We then bypass this impossibility result for the structured case of ReLU neural networks. To that end, in a practical white-box setting in which the optimizer is granted access to the network's architecture, we propose a simple, dimension-free, deterministic smoothing that provably preserves $(\delta,\epsilon)$-stationary points. Our method applies to a variety of architectures of arbitrary depth, including ResNets and ConvNets. Combined with our algorithm, this yields the first deterministic dimension-free algorithm for optimizing ReLU networks, circumventing our lower bound., Comment: This work supersedes arxiv:2209.12463 and arxiv:2209.10346[Section 3], with major additional results

Standard conformal prediction methods provide a marginal coverage guarantee, which means that for a random test point, the conformal prediction set contains the true label with a user-chosen probability. In many classification problems, we would like to obtain a stronger guarantee -- that for test points of a specific class, the prediction set contains the true label with the same user-chosen probability. Existing conformal prediction methods do not work well when there is a limited amount of labeled data per class, as is often the case in real applications where the number of classes is large. We propose a method called clustered conformal prediction, which clusters together classes that have "similar" conformal scores and then performs conformal prediction at the cluster level. Based on empirical evaluation across four image data sets with many (up to 1000) classes, we find that clustered conformal typically outperforms existing methods in terms of class-conditional coverage and set size metrics.

We exploit analogies between first-order algorithms for constrained optimization and non-smooth dynamical systems to design a new class of accelerated first-order algorithms for constrained optimization. Unlike Frank-Wolfe or projected gradients, these algorithms avoid optimization over the entire feasible set at each iteration. We prove convergence to stationary points even in a nonconvex setting and we derive rates for the convex setting. An important property of these algorithms is that constraints are expressed in terms of velocities instead of positions, which naturally leads to sparse, local and convex approximations of the feasible set (even if the feasible set is nonconvex). Thus, the complexity tends to grow mildly in the number of decision variables and in the number of constraints, which makes the algorithms suitable for machine learning applications. We apply our algorithms to a compressed sensing and a sparse regression problem, showing that we can treat nonconvex $\ell^p$ constraints ($p, 25 pages, 5 figures

Funding Information: This study was partially funded by VLIR-UOS. The study sponsors had no role in the study design, the collection, analysis and interpretation of data; in the writing of the report; and in the decision to submit the paper for publication. Publisher Copyright: © 2022, The Author(s). Background: HIV drug resistance (HIVDR) continues to threaten the effectiveness of worldwide antiretroviral therapy (ART). Emergence and transmission of HIVDR are driven by several interconnected factors. Though much has been done to uncover factors influencing HIVDR, overall interconnectedness between these factors remains unclear and African policy makers encounter difficulties setting priorities combating HIVDR. By viewing HIVDR as a complex adaptive system, through the eyes of multi-disciplinary HIVDR experts, we aimed to make a first attempt to linking different influencing factors and gaining a deeper understanding of the complexity of the system. Methods: We designed a detailed systems map of factors influencing HIVDR based on semi-structured interviews with 15 international HIVDR experts from or with experience in sub-Saharan Africa, from different disciplinary backgrounds and affiliated with different types of institutions. The resulting detailed system map was conceptualized into three main HIVDR feedback loops and further strengthened with literature evidence. Results: Factors influencing HIVDR in sub-Saharan Africa and their interactions were sorted in five categories: biology, individual, social context, healthcare system and ‘overarching’. We identified three causal loops cross-cutting these layers, which relate to three interconnected subsystems of mechanisms influencing HIVDR. The ‘adherence motivation’ subsystem concerns the interplay of factors influencing people living with HIV to alternate between adherence and non-adherence. The ‘healthcare burden’ subsystem is a reinforcing loop leading to an increase in HIVDR at local population level. The ‘ART overreliance’ subsystem is a balancing feedback loop leading to complacency among program managers when there is overreliance on ART with a perceived low risk to drug resistance. The three subsystems are interconnected at different levels. Conclusions: Interconnectedness of the three subsystems underlines the need to act on the entire system of factors surrounding HIVDR in sub-Saharan Africa in order to target interventions and to prevent unwanted effects on other parts of the system. The three theories that emerged while studying HIVDR as a complex adaptive system form a starting point for further qualitative and quantitative investigation. publishersversion published

Online platforms in the Internet Economy commonly incorporate recommender systems that recommend arms (e.g., products) to agents (e.g., users). In such platforms, a myopic agent has a natural incentive to exploit, by choosing the best product given the current information rather than to explore various alternatives to collect information that will be used for other agents. We propose a novel recommender system that respects agents' incentives and enjoys asymptotically optimal performances expressed by the regret in repeated games. We model such an incentive-aware recommender system as a multi-agent bandit problem in a two-sided market which is equipped with an incentive constraint induced by agents' opportunity costs. If the opportunity costs are known to the principal, we show that there exists an incentive-compatible recommendation policy, which pools recommendations across a genuinely good arm and an unknown arm via a randomized and adaptive approach. On the other hand, if the opportunity costs are unknown to the principal, we propose a policy that randomly pools recommendations across all arms and uses each arm's cumulative loss as feedback for exploration. We show that both policies also satisfy an ex-post fairness criterion, which protects agents from over-exploitation.

We study the hidden-action principal-agent problem in an online setting. In each round, the principal posts a contract that specifies the payment to the agent based on each outcome. The agent then makes a strategic choice of action that maximizes her own utility, but the action is not directly observable by the principal. The principal observes the outcome and receives utility from the agent's choice of action. Based on past observations, the principal dynamically adjusts the contracts with the goal of maximizing her utility. We introduce an online learning algorithm and provide an upper bound on its Stackelberg regret. We show that when the contract space is $[0,1]^m$, the Stackelberg regret is upper bounded by $\widetilde O(\sqrt{m} \cdot T^{1-1/(2m+1)})$, and lower bounded by $\Omega(T^{1-1/(m+2)})$, where $\widetilde O$ omits logarithmic factors. This result shows that exponential-in-$m$ samples are sufficient and necessary to learn a near-optimal contract, resolving an open problem on the hardness of online contract design. Moreover, when contracts are restricted to some subset $\mathcal{F} \subset [0,1]^m$, we define an intrinsic dimension of $\mathcal{F}$ that depends on the covering number of the spherical code in the space and bound the regret in terms of this intrinsic dimension. When $\mathcal{F}$ is the family of linear contracts, we show that the Stackelberg regret grows exactly as $\Theta(T^{2/3})$. The contract design problem is challenging because the utility function is discontinuous. Bounding the discretization error in this setting has been an open problem. In this paper, we identify a limited set of directions in which the utility function is continuous, allowing us to design a new discretization method and bound its error. This approach enables the first upper bound with no restrictions on the contract and action space.

We consider a model for an N × N lattice network of weakly coupled neural oscilla- tors with periodic boundary conditions (2D square torus), where the coupling between neurons is assumed to be within a von Neumann neighborhood of size r, denoted as von Neumann r-neighborhood. Using the phase model reduction technique, we study the existence of cluster solutions with constant phase differences (Ψh, Ψv) between adjacent oscillators along the horizontal and vertical directions in our network, where Ψh and Ψv are not necessarily to be identical. Applying the Kronecker production representation and the circulant matrix theory, we develop a novel approach to analyze the stability of cluster solutions with constant phase difference (i.e., Ψh,Ψv are equal). We begin our analysis by deriving the precise conditions for stability of such cluster solutions with von Neumann 1-neighborhood and 2 neighborhood couplings, and then we generalize our result to von Neumann r-neighborhood coupling for arbitrary neighborhood size r ≥ 1. This developed approach for the stability analysis indeed can be extended to an arbitrary coupling in our network. Finally, numerical simulations are used to validate the above analytical results for various values of N and r by considering an inhibitory network of Morris-Lecar neurons.

Yang et al. (2023) recently addressed the open problem of solving Variational Inequalities (VIs) with equality and inequality constraints through a first-order gradient method. However, the proposed primal-dual method called ACVI is applicable when we can compute analytic solutions of its subproblems; thus, the general case remains an open problem. In this paper, we adopt a warm-starting technique where we solve the subproblems approximately at each iteration and initialize the variables with the approximate solution found at the previous iteration. We prove its convergence and show that the gap function of the last iterate of this inexact-ACVI method decreases at a rate of $\mathcal{O}(\frac{1}{\sqrt{K}})$ when the operator is $L$-Lipschitz and monotone, provided that the errors decrease at appropriate rates. Interestingly, we show that often in numerical experiments, this technique converges faster than its exact counterpart. Furthermore, for the cases when the inequality constraints are simple, we propose a variant of ACVI named P-ACVI and prove its convergence for the same setting. We further demonstrate the efficacy of the proposed methods through numerous experiments. We also relax the assumptions in Yang et al., yielding, to our knowledge, the first convergence result that does not rely on the assumption that the operator is $L$-Lipschitz. Our source code is provided at $\texttt{https://github.com/mpagli/Revisiting-ACVI}$., arXiv admin note: text overlap with arXiv:2206.10575

We propose and analyze exact and inexact regularized Newton-type methods for finding a global saddle point of a \textit{convex-concave} unconstrained min-max optimization problem. Compared to their first-order counterparts, investigations of second-order methods for min-max optimization are relatively limited, as obtaining global rates of convergence with second-order information is much more involved. In this paper, we highlight how second-order information can be used to speed up the dynamics of dual extrapolation methods {despite inexactness}. Specifically, we show that the proposed algorithms generate iterates that remain within a bounded set and the averaged iterates converge to an $\epsilon$-saddle point within $O(\epsilon^{-2/3})$ iterations in terms of a gap function. Our algorithms match the theoretically established lower bound in this context and our analysis provides a simple and intuitive convergence analysis for second-order methods without requiring any compactness assumptions. Finally, we present a series of numerical experiments on synthetic and real data that demonstrate the efficiency of the proposed algorithms., Comment: 31 pages, 12 figures; Change the optimality notion to a more standard restricted gap function

Social and real-world considerations such as robustness, fairness, social welfare and multi-agent tradeoffs have given rise to multi-distribution learning paradigms, such as collaborative, group distributionally robust, and fair federated learning. In each of these settings, a learner seeks to minimize its worst-case loss over a set of $n$ predefined distributions, while using as few samples as possible. In this paper, we establish the optimal sample complexity of these learning paradigms and give algorithms that meet this sample complexity. Importantly, our sample complexity bounds exceed that of the sample complexity of learning a single distribution only by an additive factor of $n \log(n) / \epsilon^2$. These improve upon the best known sample complexity of agnostic federated learning by Mohri et al. by a multiplicative factor of $n$, the sample complexity of collaborative learning by Nguyen and Zakynthinou by a multiplicative factor $\log n / \epsilon^3$, and give the first sample complexity bounds for the group DRO objective of Sagawa et al. To achieve optimal sample complexity, our algorithms learn to sample and learn from distributions on demand. Our algorithm design and analysis is enabled by our extensions of stochastic optimization techniques for solving stochastic zero-sum games. In particular, we contribute variants of Stochastic Mirror Descent that can trade off between players' access to cheap one-off samples or more expensive reusable ones., Comment: 40 pages, 1 figure. Authors are ordered alphabetically. Outstanding paper award at the Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022). Version V2 updates a minor mistake in Lemma 3.1

We study reserve price optimization in multi-phase second price auctions, where seller's prior actions affect the bidders' later valuations through a Markov Decision Process (MDP). Compared to the bandit setting in existing works, the setting in ours involves three challenges. First, from the seller's perspective, we need to efficiently explore the environment in the presence of potentially nontruthful bidders who aim to manipulates seller's policy. Second, we want to minimize the seller's revenue regret when the market noise distribution is unknown. Third, the seller's per-step revenue is unknown, nonlinear, and cannot even be directly observed from the environment. We propose a mechanism addressing all three challenges. To address the first challenge, we use a combination of a new technique named "buffer periods" and inspirations from Reinforcement Learning (RL) with low switching cost to limit bidders' surplus from untruthful bidding, thereby incentivizing approximately truthful bidding. The second one is tackled by a novel algorithm that removes the need for pure exploration when the market noise distribution is unknown. The third challenge is resolved by an extension of LSVI-UCB, where we use the auction's underlying structure to control the uncertainty of the revenue function. The three techniques culminate in the $\underline{\rm C}$ontextual-$\underline{\rm L}$SVI-$\underline{\rm U}$CB-$\underline{\rm B}$uffer (CLUB) algorithm which achieves $\tilde{ \mathcal{O}}(H^{5/2}\sqrt{K})$ revenue regret when the market noise is known and $\tilde{ \mathcal{O}}(H^{3}\sqrt{K})$ revenue regret when the noise is unknown with no assumptions on bidders' truthfulness.

We propose and analyze exact and inexact regularized Newton-type methods for finding a global saddle point of a convex-concave unconstrained min-max optimization problem. Compared to their first-order counterparts, investigations of second-order methods for min-max optimization are relatively limited, as obtaining global rates of convergence with second-order information is much more involved. In this paper, we highlight how second-order information can be used to speed up the dynamics of dual extrapolation methods despite inexactness. Specifically, we show that the proposed algorithms generate iterates that remain within a bounded set and the averaged iterates converge to an ϵ-saddle point within O(ϵ −2/3) iterations in terms of a gap function. Our algorithms match the theoretically established lower bound in this context and our analysis provides a simple and intuitive convergence analysis for second-order methods without requiring any compactness assumptions. Finally, we present a series of numerical experiments on synthetic and real data that demonstrate the efficiency of the proposed algorithms.

With the increasing need for handling large state and action spaces, general function approximation has become a key technique in reinforcement learning (RL). In this paper, we propose a general framework that unifies model-based and model-free RL, and an Admissible Bellman Characterization (ABC) class that subsumes nearly all Markov Decision Process (MDP) models in the literature for tractable RL. We propose a novel estimation function with decomposable structural properties for optimization-based exploration and the functional eluder dimension as a complexity measure of the ABC class. Under our framework, a new sample-efficient algorithm namely OPtimization-based ExploRation with Approximation (OPERA) is proposed, achieving regret bounds that match or improve over the best-known results for a variety of MDP models. In particular, for MDPs with low Witness rank, under a slightly stronger assumption, OPERA improves the state-of-the-art sample complexity results by a factor of $dH$. Our framework provides a generic interface to design and analyze new RL models and algorithms.

In this paper, we present several new results on minimizing a nonsmooth and nonconvex function under a Lipschitz condition. Recent work shows that while the classical notion of Clarke stationarity is computationally intractable up to some sufficiently small constant tolerance, the randomized first-order algorithms find a $(\delta, \epsilon)$-Goldstein stationary point with the complexity bound of $\tilde{O}(\delta^{-1}\epsilon^{-3})$, which is independent of dimension $d \geq 1$~\citep{Zhang-2020-Complexity, Davis-2022-Gradient, Tian-2022-Finite}. However, the deterministic algorithms have not been fully explored, leaving open several problems in nonsmooth nonconvex optimization. Our first contribution is to demonstrate that the randomization is \textit{necessary} to obtain a dimension-independent guarantee, by proving a lower bound of $\Omega(d)$ for any deterministic algorithm that has access to both $1^{st}$ and $0^{th}$ oracles. Furthermore, we show that the $0^{th}$ oracle is \textit{essential} to obtain a finite-time convergence guarantee, by showing that any deterministic algorithm with only the $1^{st}$ oracle is not able to find an approximate Goldstein stationary point within a finite number of iterations up to sufficiently small constant parameter and tolerance. Finally, we propose a deterministic smoothing approach under the \textit{arithmetic circuit} model where the resulting smoothness parameter is exponential in a certain parameter $M > 0$ (e.g., the number of nodes in the representation of the function), and design a new deterministic first-order algorithm that achieves a dimension-independent complexity bound of $\tilde{O}(M\delta^{-1}\epsilon^{-3})$., Comment: 28 Pages; Fix an error and add relevant references

We study a constructive algorithm that approximates Gateaux derivatives for statistical functionals by finite differencing, with a focus on functionals that arise in causal inference. We study the case where probability distributions are not known a priori but need to be estimated from data. These estimated distributions lead to empirical Gateaux derivatives, and we study the relationships between empirical, numerical, and analytical Gateaux derivatives. Starting with a case study of the interventional mean (average potential outcome), we delineate the relationship between finite differences and the analytical Gateaux derivative. We then derive requirements on the rates of numerical approximation in perturbation and smoothing that preserve the statistical benefits of one-step adjustments, such as rate double robustness. We then study more complicated functionals such as dynamic treatment regimes, the linear-programming formulation for policy optimization in infinite-horizon Markov decision processes, and sensitivity analysis in causal inference. More broadly, we study optimization-based estimators, since this begets a class of estimands where identification via regression adjustment is straightforward but obtaining influence functions under minor variations thereof is not. The ability to approximate bias adjustments in the presence of arbitrary constraints illustrates the usefulness of constructive approaches for Gateaux derivatives. We also find that the statistical structure of the functional (rate double robustness) can permit less conservative rates for finite-difference approximation. This property, however, can be specific to particular functionals; e.g., it occurs for the average potential outcome (hence average treatment effect) but not the infinite-horizon MDP policy value., Extended version of conference version "Empirical Gateaux Derivatives for Causal Inference" accepted at Neurips 2022; new results on optimization and sensitivity analysis

Funding Information: This work was funded by VLIR-UOS, grant numbers TZ2019SIN263 and TZ2020JOI032A101. Publisher Copyright: © Concern is justified observing the link between the AIDS and COVID-19 pandemics. COVID-19 outcomes are significantly worse in many people living with HIV (PLHIV), even when vaccinated, because of their impaired immune system. Moreover, CD4 T-cells are affected by both HIV and SARS-CoV-2.1-3 SARS-CoV-2 variants can evolve in immunosuppressed patients due to prolonged viral replication in the context of an inadequate immune response.4 Accelerated intrahost evolution of SARS-CoV-2 was reported in a South African HIV patient with antiretroviral therapy (ART) failure.5 6 With 25 million HIV patients in sub-Saharan Africa (SSA) of whom an estimated 8 million are not virologically suppressed, this potentially creates a reservoir for future variants. Such variants, arising in PLHIV anywhere in the world, can spread to other continents, as has been reported for variants of concern (VoCs) (Beta, Omicron) and variants of interest (B.1.6.20, B.1.640.2) that arose in Africa.7-9 Conversely, the COVID-19 pandemic impacts HIV treatment programmes, due to supply chain issues, overburdening of healthcare systems, limiting access to testing, treatment and prevention programmes and further increasing inequalities.10 Modelled COVID-19 disruptions of HIV programmes in SSA included decreased functionality of HIV prevention programmes, HIV testing and treatment, healthcare services such as viral load testing, adherence counselling, drug regimen switches and ART interruptions, which may lead to selection of drug-resistant HIV.11 A 6-month interruption affecting 50% of the population would lead to a median number of excess deaths of 296 000, during 1 year. Scientists advocate for the AIDS and COVID-19 pandemics in Africa to be addressed simultaneously, by increasing African access to COVID-19 vaccines, prioritising research on the interaction between HIV care and COVID-19, maintaining high-quality HIV services and integrating health services for both viruses.7 Both the COVID-19 and the AIDS pandemic, more specifically the issue of HIV drug resistance (HIVDR), have previously been described as wicked problems which are best studied as complex adaptive systems (CASs).12-15Wicked problems consist of diverse interconnected factors and require complexity-informed and locally adapted solutions rather than one solution that fits all. We recently designed a qualitative model of all known factors influencing HIVDR in SSA and analysed its complexity.13 Our detailed systems map featured three main feedback loops driving HIVDR, representing (1) the alternation between adherence and non-adherence, (2) the impact of an overburdened healthcare system and (3) the importance of sustaining global efforts of tackling HIVDR even when new antiretroviral drugs with high genetic barriers become available. These HIV-related feedback loops are interconnected with COVID-19 pandemic impact (in yellow, figure 1). The loop starts from PLHIV with an unsuppressed viral load, which weakens the immune system and may in turn slow down immune clearance of SARS-CoV-2, allowing prolonged replication and mutation of the virus in the context of an inadequate immune response. Prolonged viral clearance facilitates the selection of immune escape SARS-CoV-2 variants. Variants may emerge that have a selective advantage and therefore may spread through populations due to increased transmissibility (with possibly increased virulence), thereby creating an additional burden on the healthcare system, putting the overall healthcare system and the HIV care at risk. These stressors on the healthcare system lead to a higher risk of unsuppressed viral load in PLHIV, increasing the risk of HIVDR. Figure 1 shows the need to address both wicked problems simultaneously and to do so in a complexity-informed manner as they are inevitably linked and influence each other. Evidently, the exact interconnections between both pandemics need to be locally assessed. For instance, a study in South Africa showed that while lockdown severely impacted HIV testing and ART initiation, ART provision was largely maintained, indicating that the strength of the connection between the virological suppression-related loop and the pandemic, indicated in figure 1, are context-dependent.16 publishersversion published

Algorithms that solve zero-sum games, multi-objective agent objectives, or, more generally, variational inequality (VI) problems are notoriously unstable on general problems. Owing to the increasing need for solving such problems in machine learning, this instability has been highlighted in recent years as a significant research challenge. In this paper, we provide an overview of recent progress in the use of continuous-time perspectives in the analysis and design of methods targeting the broad VI problem class. Our presentation draws parallels between single-objective problems and multi-objective problems, highlighting the challenges of the latter. We also formulate various desiderata for algorithms that apply to general VIs and we argue that achieving these desiderata may profit from an understanding of the associated continuous-time dynamics.

State-of-the-art federated learning methods can perform far worse than their centralized counterparts when clients have dissimilar data distributions. For neural networks, even when centralized SGD easily finds a solution that is simultaneously performant for all clients, current federated optimization methods fail to converge to a comparable solution. We show that this performance disparity can largely be attributed to optimization challenges presented by nonconvexity. Specifically, we find that the early layers of the network do learn useful features, but the final layers fail to make use of them. That is, federated optimization applied to this non-convex problem distorts the learning of the final layers. Leveraging this observation, we propose a Train-Convexify-Train (TCT) procedure to sidestep this issue: first, learn features using off-the-shelf methods (e.g., FedAvg); then, optimize a convexified problem obtained from the network's empirical neural tangent kernel approximation. Our technique yields accuracy improvements of up to +36% on FMNIST and +37% on CIFAR10 when clients have dissimilar data., Accepted at Neural Information Processing Systems (NeurIPS) 2022. V2 releases code

Content creators compete for user attention. Their reach crucially depends on algorithmic choices made by developers on online platforms. To maximize exposure, many creators adapt strategically, as evidenced by examples like the sprawling search engine optimization industry. This begets competition for the finite user attention pool. We formalize these dynamics in what we call an exposure game, a model of incentives induced by algorithms, including modern factorization and (deep) two-tower architectures. We prove that seemingly innocuous algorithmic choices, e.g., non-negative vs. unconstrained factorization, significantly affect the existence and character of (Nash) equilibria in exposure games. We proffer use of creator behavior models, like exposure games, for an (ex-ante) pre-deployment audit. Such an audit can identify misalignment between desirable and incentivized content, and thus complement post-hoc measures like content filtering and moderation. To this end, we propose tools for numerically finding equilibria in exposure games, and illustrate results of an audit on the MovieLens and LastFM datasets. Among else, we find that the strategically produced content exhibits strong dependence between algorithmic exploration and content diversity, and between model expressivity and bias towards gender-based user and creator groups., presented at ICLR 2023 (top 5%)

We develop an interior-point approach to solve constrained variational inequality (cVI) problems. Inspired by the efficacy of the alternating direction method of multipliers (ADMM) method in the single-objective context, we generalize ADMM to derive a first-order method for cVIs, that we refer to as ADMM-based interior-point method for constrained VIs (ACVI). We provide convergence guarantees for ACVI in two general classes of problems: (i) when the operator is $\xi$-monotone, and (ii) when it is monotone, some constraints are active and the game is not purely rotational. When the operator is, in addition, L-Lipschitz for the latter case, we match known lower bounds on rates for the gap function of $\mathcal{O}(1/\sqrt{K})$ and $\mathcal{O}(1/K)$ for the last and average iterate, respectively. To the best of our knowledge, this is the first presentation of a first-order interior-point method for the general cVI problem that has a global convergence guarantee. Moreover, unlike previous work in this setting, ACVI provides a means to solve cVIs when the constraints are nontrivial. Empirical analyses demonstrate clear advantages of ACVI over common first-order methods. In particular, (i) cyclical behavior is notably reduced as our methods approach the solution from the analytic center, and (ii) unlike projection-based methods that zigzag when near a constraint, ACVI efficiently handles the constraints.

We consider the smooth convex-concave bilinearly-coupled saddle-point problem, $\min_{\mathbf{x}}\max_{\mathbf{y}}~F(\mathbf{x}) + H(\mathbf{x},\mathbf{y}) - G(\mathbf{y})$, where one has access to stochastic first-order oracles for $F$, $G$ as well as the bilinear coupling function $H$. Building upon standard stochastic extragradient analysis for variational inequalities, we present a stochastic \emph{accelerated gradient-extragradient (AG-EG)} descent-ascent algorithm that combines extragradient and Nesterov's acceleration in general stochastic settings. This algorithm leverages scheduled restarting to admit a fine-grained nonasymptotic convergence rate that matches known lower bounds by both \citet{ibrahim2020linear} and \citet{zhang2021lower} in their corresponding settings, plus an additional statistical error term for bounded stochastic noise that is optimal up to a constant prefactor. This is the first result that achieves such a relatively mature characterization of optimality in saddle-point optimization., More polishing and clarifications; 36 pages

Technology ecosystems often undergo significant transformations as they mature. For example, telephony, the Internet, and PCs all started with a single provider, but in the United States each is now served by a competitive market that uses comprehensive and universal technology standards to provide compatibility. This white paper presents our view on how the cloud ecosystem, barely over fifteen years old, could evolve as it matures., Comment: 35 pages

We settle an open and challenging question pertaining to the design of simple and optimal high-order methods for solving smooth and monotone variational inequalities (VIs). A VI involves finding $x^\star \in \mathcal{X}$ such that $\langle F(x), x - x^\star\rangle \geq 0$ for all $x \in \mathcal{X}$ and we consider the setting in which $F: \mathbb{R}^d \mapsto \mathbb{R}^d$ is smooth with up to $(p-1)^{th}$-order derivatives. For $p = 2$, the cubic regularized Newton's method has been extended to VIs with a global rate of $O(\epsilon^{-1})$. An improved rate of $O(\epsilon^{-2/3}\log\log(1/\epsilon))$ can be obtained via an alternative second-order method, but this method requires a nontrivial line-search procedure as an inner loop. Similarly, high-order methods based on similar line-search procedures have been shown to achieve a rate of $O(\epsilon^{-2/(p+1)}\log\log(1/\epsilon))$, but the inner loop requires fine-tuning of parameters and can be computationally complex. As highlighted by Nesterov, it would be desirable to develop a simple high-order VI method that retains the optimality of the more complex methods. We propose a $p^{th}$-order method that does \textit{not} require any search procedure and provably converges to a weak solution at a rate of $O(\epsilon^{-2/(p+1)})$. We prove that our $p^{th}$-order method is optimal in the monotone setting by establishing a lower bound of $\Omega(\epsilon^{-2/(p+1)})$ under a linear span assumption. A version with restarting attains a global linear and local superlinear convergence rate for smooth and strongly monotone VIs. Furthermore, our method achieves a global rate of $O(\epsilon^{-2/p})$ for solving smooth and nonmonotone VIs satisfying the Minty condition. The restarted version again attains a global linear and local superlinear convergence rate if the strong Minty condition is satisfied., Comment: Improve the paper writing significantly; 38 pages

In this chapter, we identify fundamental geometric structures that underlie the problems of sampling, optimisation, inference and adaptive decision-making. Based on this identification, we derive algorithms that exploit these geometric structures to solve these problems efficiently. We show that a wide range of geometric theories emerge naturally in these fields, ranging from measure-preserving processes, information divergences, Poisson geometry, and geometric integration. Specifically, we explain how (i) leveraging the symplectic geometry of Hamiltonian systems enable us to construct (accelerated) sampling and optimisation methods, (ii) the theory of Hilbertian subspaces and Stein operators provides a general methodology to obtain robust estimators, (iii) preserving the information geometry of decision-making yields adaptive agents that perform active inference. Throughout, we emphasise the rich connections between these fields; e.g., inference draws on sampling and optimisation, and adaptive decision-making assesses decisions by inferring their counterfactual consequences. Our exposition provides a conceptual overview of underlying ideas, rather than a technical discussion, which can be found in the references herein., 30 pages, 4 figures; 42 pages including table of contents and references

In today's economy, it becomes important for Internet platforms to consider the sequential information design problem to align its long term interest with incentives of the gig service providers. This paper proposes a novel model of sequential information design, namely the Markov persuasion processes (MPPs), where a sender, with informational advantage, seeks to persuade a stream of myopic receivers to take actions that maximizes the sender's cumulative utilities in a finite horizon Markovian environment with varying prior and utility functions. Planning in MPPs thus faces the unique challenge in finding a signaling policy that is simultaneously persuasive to the myopic receivers and inducing the optimal long-term cumulative utilities of the sender. Nevertheless, in the population level where the model is known, it turns out that we can efficiently determine the optimal (resp. $\epsilon$-optimal) policy with finite (resp. infinite) states and outcomes, through a modified formulation of the Bellman equation. Our main technical contribution is to study the MPP under the online reinforcement learning (RL) setting, where the goal is to learn the optimal signaling policy by interacting with with the underlying MPP, without the knowledge of the sender's utility functions, prior distributions, and the Markov transition kernels. We design a provably efficient no-regret learning algorithm, the Optimism-Pessimism Principle for Persuasion Process (OP4), which features a novel combination of both optimism and pessimism principles. Our algorithm enjoys sample efficiency by achieving a sublinear $\sqrt{T}$-regret upper bound. Furthermore, both our algorithm and theory can be applied to MPPs with large space of outcomes and states via function approximation, and we showcase such a success under the linear setting.