Search

Remote estimation is a crucial element of real time monitoring of a stochastic process. While most of the existing works have concentrated on obtaining optimal sampling strategies, motivated by malicious attacks on cyber-physical systems, we model sensing under surveillance as a game between an attacker and a defender. This introduces strategic elements to conventional remote estimation problems. Additionally, inspired by increasing detection capabilities, we model an element of information leakage for each player. Parameterizing the game in terms of uncertainty on each side, information leakage, and cost of sampling, we consider the Stackelberg Equilibrium (SE) concept where one of the players acts as the leader and the other one as the follower. By focusing our attention on stationary probabilistic sampling policies, we characterize the SE of this game and provide simulations to show the efficacy of our results.

The development of extremum seeking (ES) has progressed, over the past hundred years, from static maps, to finite-dimensional dynamic systems, to networks of static and dynamic agents. Extensions from ODE dynamics to maps and agents that incorporate delays or even partial differential equations (PDEs) is the next natural step in that progression through ascending research challenges. This paper reviews results on algorithm design and theory of ES for such infinite-dimensional systems. Both hyperbolic and parabolic dynamics are presented: delays or transport equations, heat-dominated equation, wave equations, and reaction-advection-diffusion equations. Nash equilibrium seeking (NES) methods are introduced for noncooperative game scenarios of the model-free kind and then specialized to single-agent optimization. Even heterogeneous PDE games, such as a duopoly with one parabolic and one hyperbolic agent, are considered. Several engineering applications are touched upon for illustration, including flow-traffic control for urban mobility, oil-drilling systems, deep-sea cable-actuated source seeking, additive manufacturing modeled by the Stefan PDE, biological reactors, light-source seeking with flexible-beam structures, and neuromuscular electrical stimulation., Comment: Preprint submitted to IEEE Control Systems Magazine (Special Issue: Into the Second Century of Extremum Seeking Control, 38 pages and 34 figures)

Conway's Game of Life (GOL) is an epitome showing how complex dynamical behavior emerges from simple local interactions. Although it has often been found that GOL dynamics lies close to critical behavior, this system has never been studied in the context of a deterministic phase transitions and cluster dynamics. In this work, we study the deterministic critical behavior that emerges in the \textit{logistic} GOL: an extension of Conway's GOL with a parameter that alters the dynamics by expanding the binary state space into a Cantor set, but while maintaining the deterministic nature of the system. Upon tuning the parameter, we find that the logistic GOL comprises at least three types of asymptotic behavior, i.e phases, that are separated by two critical points. One critical point defines the boundary between a sparse-static and a sparse-dynamic asymptotic phase, whereas the other point marks a deterministic percolation transition between the sparse-dynamic and a third, dense-dynamic asymptotic phase. Moreover, we identify distinct power-law distributions of cluster sizes near the critical points, and discuss the underlying mechanisms that give rise to such critical behavior. Overall, our work highlights that scale invariance can emerge even when clusters in a system are generated by a purely deterministic process., Comment: 20 pages,16 figures

This study investigates the efficacy of Multi-Agent Systems in eliciting cross-agent communication and enhancing collective intelligence through group decision-making in a decentralized setting. Unlike centralized mechanisms, where a fixed hierarchy governs social choice, decentralized group decision-making allows agents to engage in joint deliberation. Our research focuses on the dynamics of communication and decision-making within various social choice methods. By applying different voting rules in various environments, we find that moderate decision flexibility yields better outcomes. Additionally, exploring the linguistic features of agent-to-agent conversations reveals indicators of effective collaboration, offering insights into communication patterns that facilitate or hinder collaboration. Finally, we propose various methods for determining the optimal stopping point in multi-agent collaborations based on linguistic cues. Our findings contribute to a deeper understanding of how decentralized decision-making and group conversation shape multi-agent collaboration, with implications for the design of more effective MAS environments., Comment: preprint

Vaccination is an effective strategy to prevent the spread of diseases. However, hesitancy and rejection of vaccines, particularly in childhood immunizations, pose challenges to vaccination efforts. In that case, according to rational decision-making and classical utility theory, parents weigh the costs of vaccinating against the costs of not vaccinating their children. Social norms influence these parental decision-making outcomes, further deviating their decisions from rationality. Additionally, variability in values of utilities stemming from stochasticity in parents' perceptions over time can lead to further deviations from rationality. In this paper, we employ independent white noises to represent stochastic fluctuations in parental perceptions of utility functions of the decisions over time as well as in the disease transmission rates. This approach leads to a system of stochastic differential equations of a susceptible-infected-recovered (SIR) model coupled with a stochastic replicator equation. We explore the dynamics of these equations and identify new behaviors emerging from stochastic influences. Interestingly, incorporating stochasticity into the utility functions for vaccination and nonvaccination leads to a decision-making model that reflects the bounded rationality of humans. Noise, like social norms, is a two-sided sword that depends on the degree of bounded rationality of each group. We finally perform a stochastic optimal control as a discount to cost of vaccination to counteract bounded rationality., Comment: 38 pages, 7 figures

This paper discusses further evaluations of the educational effectiveness of an existing CPU visual simulator (CPUVSIM). The CPUVSIM, as an Open Educational Resource, has been iteratively improved over a number of years following an Open Pedagogy approach, and was designed to enhance novices understanding of computer operation and mapping from high-level code to assembly language. The literature reports previous evaluations of the simulator, at K12 and undergraduate level, conducted from the perspectives of both developers and students, albeit with a limited sample size and primarily through qualitative methods. This paper describes additional evaluation activities designed to provide a more comprehensive assessment, across diverse educational settings: an action research pilot study recently carried out in Singapore and the planning of a more quantitative-oriented study in Dubai, with a larger sample size. Results from the pilot study in Singapore confirm the effectiveness and high level of appreciation of the tool, alongside a few identified challenges, which inform the planning of the more comprehensive evaluation in Dubai., Comment: 8 pages

In this work, we study $\gamma$-discounted infinite-horizon tabular Markov decision processes (MDPs) and introduce a framework called dynamic policy gradient (DynPG). The framework directly integrates dynamic programming with (any) policy gradient method, explicitly leveraging the Markovian property of the environment. DynPG dynamically adjusts the problem horizon during training, decomposing the original infinite-horizon MDP into a sequence of contextual bandit problems. By iteratively solving these contextual bandits, DynPG converges to the stationary optimal policy of the infinite-horizon MDP. To demonstrate the power of DynPG, we establish its non-asymptotic global convergence rate under the tabular softmax parametrization, focusing on the dependencies on salient but essential parameters of the MDP. By combining classical arguments from dynamic programming with more recent convergence arguments of policy gradient schemes, we prove that softmax DynPG scales polynomially in the effective horizon $(1-\gamma)^{-1}$. Our findings contrast recent exponential lower bound examples for vanilla policy gradient., Comment: 46 pages, 4 figures

I report on the first observed self-amplification by stimulated emission of 0.2THz and 1.63THz radiation using InGaAs/GaAs HEMT operating in the deep saturation regime at room temperature. I demonstrate both theoretically and experimentally that the Sub-THz and THz FETs response is due to rectification of the nonlinear dependence of the device current-voltage characteristics. FETs do operate as a nonlinear THz mixers and rectifiers and its open-drain responsivity is given by a similar expression to that of zero-bias Schottky diode detector. However, operating FETs deep in the saturation regime does allow the accurate tuning of the device to the resonance condition or the negative resistance mode at room temperature, hence FETs can be tuned in the deep saturation regime to enable sub-THz and THz lasing effect. This observed sub-THz and THz laser phenomena using FETs will revolutionize human technology in all fields of life in the near future., Comment: 5 pages, 5 figures, to be submitted in Journal

Socio-technical networks represent emerging cyber-physical infrastructures that are tightly interwoven with human networks. The coupling between human and technical networks presents significant challenges in managing, controlling, and securing these complex, interdependent systems. This paper investigates game-theoretic frameworks for the design and control of socio-technical networks, with a focus on critical applications such as misinformation management, infrastructure optimization, and resilience in socio-cyber-physical systems (SCPS). Core methodologies, including Stackelberg games, mechanism design, and dynamic game theory, are examined as powerful tools for modeling interactions in hierarchical, multi-agent environments. Key challenges addressed include mitigating human-driven vulnerabilities, managing large-scale system dynamics, and countering adversarial threats. By bridging individual agent behaviors with overarching system goals, this work illustrates how the integration of game theory and control theory can lead to robust, resilient, and adaptive socio-technical networks. This paper highlights the potential of these frameworks to dynamically align decentralized agent actions with system-wide objectives of stability, security, and efficiency.

Musical dynamics form a core part of expressive singing voice performances. However, automatic analysis of musical dynamics for singing voice has received limited attention partly due to the scarcity of suitable datasets and a lack of clear evaluation frameworks. To address this challenge, we propose a methodology for dataset curation. Employing the proposed methodology, we compile a dataset comprising 509 musical dynamics annotated singing voice performances, aligned with 163 score files, leveraging state-of-the-art source separation and alignment techniques. The scores are sourced from the OpenScore Lieder corpus of romantic-era compositions, widely known for its wealth of expressive annotations. Utilizing the curated dataset, we train a multi-head attention based CNN model with varying window sizes to evaluate the effectiveness of estimating musical dynamics. We explored two distinct perceptually motivated input representations for the model training: log-Mel spectrum and bark-scale based features. For testing, we manually curate another dataset of 25 musical dynamics annotated performances in collaboration with a professional vocalist. We conclude through our experiments that bark-scale based features outperform log-Mel-features for the task of singing voice dynamics prediction. The dataset along with the code is shared publicly for further research on the topic., Comment: To be published in ISMIR 2024, 6 pages

We consider an information update system on a gossip network, where a source node encodes information into $n$ total keys such that any subset of at least $k+1$ keys can fully reconstruct the original information. This encoding process follows the principles of a $k$-out-of-$n$ threshold system. The encoded updates are then disseminated across the network through peer-to-peer communication. We have two different types of nodes in a network: subscriber nodes, which receive a unique key from the source node for every status update instantaneously, and nonsubscriber nodes, which receive a unique key for an update only if the node is selected by the source, and this selection is renewed for each update. For the message structure between nodes, we consider two different schemes: a memory scheme (in which the nodes keep the source's current and previous encrypted messages) and a memoryless scheme (in which the nodes are allowed to only keep the source's current message). We measure the timeliness of information updates by using a recent performance metric, the version age of information. We present explicit formulas for the time average AoI in a scalable homogeneous network as functions of the network parameters under a memoryless scheme. Additionally, we provide strict lower and upper bounds for the time average AoI under a memory scheme., Comment: A part of this work is presented at the ACSSC24. This work has been submitted to IEEE for possible publication. arXiv admin note: text overlap with arXiv:2402.11462

We study the identification and estimation of heterogeneous, intertemporal treatment effects (TE) when potential outcomes depend on past treatments. First, applying a dynamic panel data model to observed outcomes, we show that instrument-based GMM estimators, such as Arellano and Bond (1991), converge to a non-convex (negatively weighted) aggregate of TE plus non-vanishing trends. We then provide restrictions on sequential exchangeability (SE) of treatment and TE heterogeneity that reduce the GMM estimand to a convex (positively weighted) aggregate of TE. Second, we introduce an adjusted inverse-propensity-weighted (IPW) estimator for a new notion of average treatment effect (ATE) over past observed treatments. Third, we show that when potential outcomes are generated by dynamic panel data models with homogeneous TE, such GMM estimators converge to causal parameters (even when SE is generically violated without conditioning on individual fixed effects). Finally, we motivate SE and compare it with parallel trends (PT) in various settings with observational data (when treatments are dynamic, rational choices under learning) or experimental data (when treatments are sequentially randomized).

A class of simultaneous equation models arise in the many domains where observed binary outcomes are themselves a consequence of the existing choices of of one of the agents in the model. These models are gaining increasing interest in the computer science and machine learning literatures where they refer the potentially endogenous sample selection as the {\em selective labels} problem. Empirical settings for such models arise in fields as diverse as criminal justice, health care, and insurance. For important recent work in this area, see for example Lakkaruju et al. (2017), Kleinberg et al. (2018), and Coston et al.(2021) where the authors focus on judicial bail decisions, and where one observes the outcome of whether a defendant filed to return for their court appearance only if the judge in the case decides to release the defendant on bail. Identifying and estimating such models can be computationally challenging for two reasons. One is the nonconcavity of the bivariate likelihood function, and the other is the large number of covariates in each equation. Despite these challenges, in this paper we propose a novel distribution free estimation procedure that is computationally friendly in many covariates settings. The new method combines the semiparametric batched gradient descent algorithm introduced in Khan et al.(2023) with a novel sorting algorithms incorporated to control for selection bias. Asymptotic properties of the new procedure are established under increasing dimension conditions in both equations, and its finite sample properties are explored through a simulation study and an application using judicial bail data.

In this paper, we introduce a method for fine-tuning Large Language Models (LLMs), inspired by Multi-Task learning in a federated manner. Our approach leverages the structure of each client's model and enables a learning scheme that considers other clients' tasks and data distribution. To mitigate the extensive computational and communication overhead often associated with LLMs, we utilize a parameter-efficient fine-tuning method, specifically Low-Rank Adaptation (LoRA), reducing the number of trainable parameters. Experimental results, with different datasets and models, demonstrate the proposed method's effectiveness compared to existing frameworks for federated fine-tuning of LLMs in terms of average and local performances. The proposed scheme outperforms existing baselines by achieving lower local loss for each client while maintaining comparable global performance.

We address counterfactual analysis in empirical models of games with partially identified parameters, and multiple equilibria and/or randomized strategies, by constructing and analyzing the counterfactual predictive distribution set (CPDS). This framework accommodates various outcomes of interest, including behavioral and welfare outcomes. It allows a variety of changes to the environment to generate the counterfactual, including modifications of the utility functions, the distribution of utility determinants, the number of decision makers, and the solution concept. We use a Bayesian approach to summarize statistical uncertainty. We establish conditions under which the population CPDS is sharp from the point of view of identification. We also establish conditions under which the posterior CPDS is consistent if the posterior distribution for the underlying model parameter is consistent. Consequently, our results can be employed to conduct counterfactual analysis after a preliminary step of identifying and estimating the underlying model parameter based on the existing literature. Our consistency results involve the development of a new general theory for Bayesian consistency of posterior distributions for mappings of sets. Although we primarily focus on a model of a strategic game, our approach is applicable to other structural models with similar features.

Estimation of near-wall turbulence in channel flow from outer observations is investigated using adjoint-variational data assimilation. We first consider fully resolved velocity data, starting at a distance from the wall. By enforcing the estimated flow to exactly satisfy the Navier-Stokes equations, we seek a statistically stationary turbulent state that reproduces the instantaneous outer measurements. Such an estimated state provides full access to the unknown near-wall turbulence, including the wall shear stresses and pressure. When the first observation is within fifty viscous units from the wall, the correlation coefficient between the true and estimated state exceeds 95%. As the observations are further separated from the wall, at ninety viscous units, the accuracy of the assimilated wall stresses decreases to 40% at the wall. This trend is nearly independent of the Reynolds number. The Fourier spectrum of the estimation error is qualitatively consistent with the coherence spectrum between the outer and the inner state variables: observed long wavelength structures in the outer flow have deeper coherence into the unobserved near-wall region, and therefore the error is lowest at large scales. Nevertheless, the adjoint-variational approach provides a more rigorous quantification of the capacity to accurately predict the instantaneous near-wall turbulence from outer measurements. Lastly, we demonstrate the robustness of the estimation accuracy using filtered and sub-sampled outer observations.

While in classical cryptography, one-way functions (OWFs) are widely regarded as the "minimal assumption," the situation in quantum cryptography is less clear. Recent works have put forward two concurrent candidates for the minimal assumption in quantum cryptography: One-way state generators (OWSGs), postulating the existence of a hard search problem with an efficient verification algorithm, and EFI pairs, postulating the existence of a hard distinguishing problem. Two recent papers [Khurana and Tomer STOC'24; Batra and Jain FOCS'24] showed that OWSGs imply EFI pairs, but the reverse direction remained open. In this work, we give strong evidence that the opposite direction does not hold: We show that there is a quantum unitary oracle relative to which EFI pairs exist, but OWSGs do not. In fact, we show a slightly stronger statement that holds also for EFI pairs that output classical bits (QEFID). As a consequence, we separate, via our oracle, QEFID, and one-way puzzles from OWSGs and several other Microcrypt primitives, including efficiently verifiable one-way puzzles and unclonable state generators. In particular, this solves a problem left open in [Chung, Goldin, and Gray Crypto'24]. Using similar techniques, we also establish a fully black-box separation (which is slightly weaker than an oracle separation) between private-key quantum money schemes and QEFID pairs. One conceptual implication of our work is that the existence of an efficient verification algorithm may lead to qualitatively stronger primitives in quantum cryptography., Comment: Minor corrections and typos were addressed in version 2

As our world digitizes, web agents that can automate complex and monotonous tasks are becoming essential in streamlining workflows. This paper introduces an approach to improving web agent performance through multi-modal validation and self-refinement. We present a comprehensive study of different modalities (text, vision) and the effect of hierarchy for the automatic validation of web agents, building upon the state-of-the-art Agent-E web automation framework. We also introduce a self-refinement mechanism for web automation, using the developed auto-validator, that enables web agents to detect and self-correct workflow failures. Our results show significant gains on Agent-E's (a SOTA web agent) prior state-of-art performance, boosting task-completion rates from 76.2\% to 81.24\% on the subset of the WebVoyager benchmark. The approach presented in this paper paves the way for more reliable digital assistants in complex, real-world scenarios.

Connectivity queries, which check whether vertices belong to the same connected component, are fundamental in graph computations. Sliding window connectivity processes these queries over sliding windows, facilitating real-time streaming graph analytics. However, existing methods struggle with low-latency processing due to the significant overhead of continuously updating index structures as edges are inserted and deleted. We introduce a novel approach that leverages spanning trees to efficiently process queries. The novelty of this method lies in its ability to maintain spanning trees efficiently as window updates occur. Notably, our approach completely eliminates the need for replacement edge searches, a traditional bottleneck in managing spanning trees during edge deletions. We also present several optimizations to maximize the potential of spanning-tree-based indexes. Our comprehensive experimental evaluation shows that index update latency in spanning trees can be reduced by up to 458x while maintaining query performance, leading to an 8x improvement in throughput. Our approach also significantly outperforms the state-of-the-art in both query processing and index updates. Additionally, our methods use significantly less memory and demonstrate consistent efficiency across various settings.

In scientific research, charts are usually the primary method for visually representing data. However, the accessibility of charts remains a significant concern. In an effort to improve chart understanding pipelines, we focus on optimizing the chart classification component. We leverage curriculum learning, which is inspired by the human learning process. In this paper, we introduce a novel training approach for chart classification that utilizes coarse-to-fine curriculum learning. Our approach, which we name C2F-CHART (for coarse-to-fine) exploits inter-class similarities to create learning tasks of varying difficulty levels. We benchmark our method on the ICPR 2022 CHART-Infographics UB UNITEC PMC dataset, outperforming the state-of-the-art results., Comment: This paper has been accepted for publication in the proceedings of the 2024 International Conference on Pattern Recognition (ICPR)

Speech emotion recognition (SER) has made significant strides with the advent of powerful self-supervised learning (SSL) models. However, the generalization of these models to diverse languages and emotional expressions remains a challenge. We propose a large-scale benchmark to evaluate the robustness and adaptability of state-of-the-art SER models in both in-domain and out-of-domain settings. Our benchmark includes a diverse set of multilingual datasets, focusing on less commonly used corpora to assess generalization to new data. We employ logit adjustment to account for varying class distributions and establish a single dataset cluster for systematic evaluation. Surprisingly, we find that the Whisper model, primarily designed for automatic speech recognition, outperforms dedicated SSL models in cross-lingual SER. Our results highlight the need for more robust and generalizable SER models, and our benchmark serves as a valuable resource to drive future research in this direction., Comment: Accepted at INTERSPEECH 2024

Most existing stochastic models on age of information (AoI) focus on a single shared server serving status update packets from $N>1$ sources where each packet update stream is Poisson, i.e., single-hop scenario. In the current work, we study a two-hop edge computing system for which status updates from the information sources are still Poisson but they are not immediately available at the shared edge server, but instead they need to first receive service from a transmission server dedicated to each source. For exponentially distributed and heterogeneous service times for both the dedicated servers and the edge server, and bufferless preemptive resource management, we develop an analytical model using absorbing Markov chains (AMC) for obtaining the distribution of AoI for any source in the system. Moreover, for a given tagged source, the traffic arriving at the shared server from the $N-1$ un-tagged sources, namely the interference traffic, is not Poisson any more, but is instead a Markov modulated Poisson process (MMPP) whose state space grows exponentially with $N$. Therefore, we propose to employ a model reduction technique that approximates the behavior of the MMPP interference traffic with two states only, making it possible to approximately obtain the AoI statistics even for a very large number of sources. Numerical examples are presented to validate the proposed exact and approximate models., Comment: 9 pages, 4 figures

This paper presents an overview of the Arabic Natural Language Understanding (ArabicNLU 2024) shared task, focusing on two subtasks: Word Sense Disambiguation (WSD) and Location Mention Disambiguation (LMD). The task aimed to evaluate the ability of automated systems to resolve word ambiguity and identify locations mentioned in Arabic text. We provided participants with novel datasets, including a sense-annotated corpus for WSD, called SALMA with approximately 34k annotated tokens, and the IDRISI-DA dataset with 3,893 annotations and 763 unique location mentions. These are challenging tasks. Out of the 38 registered teams, only three teams participated in the final evaluation phase, with the highest accuracy being 77.8% for WSD and the highest MRR@1 being 95.0% for LMD. The shared task not only facilitated the evaluation and comparison of different techniques, but also provided valuable insights and resources for the continued advancement of Arabic NLU technologies., Comment: In Proceedings of the Second Arabic Natural Language Processing Conference (ArabicNLP 2024), Bangkok, Thailand. Association for Computational Linguistics

AI Agents are changing the way work gets done, both in consumer and enterprise domains. However, the design patterns and architectures to build highly capable agents or multi-agent systems are still developing, and the understanding of the implication of various design choices and algorithms is still evolving. In this paper, we present our work on building a novel web agent, Agent-E \footnote{Our code is available at \url{https://github.com/EmergenceAI/Agent-E}}. Agent-E introduces numerous architectural improvements over prior state-of-the-art web agents such as hierarchical architecture, flexible DOM distillation and denoising method, and the concept of \textit{change observation} to guide the agent towards more accurate performance. We first present the results of an evaluation of Agent-E on WebVoyager benchmark dataset and show that Agent-E beats other SOTA text and multi-modal web agents on this benchmark in most categories by 10-30\%. We then synthesize our learnings from the development of Agent-E into general design principles for developing agentic systems. These include the use of domain-specific primitive skills, the importance of distillation and de-noising of environmental observations, the advantages of a hierarchical architecture, and the role of agentic self-improvement to enhance agent efficiency and efficacy as the agent gathers experience.

Evolutional deep neural networks (EDNN) solve partial differential equations (PDEs) by marching the network representation of the solution fields, using the governing equations. Use of a single network to solve coupled PDEs on large domains requires a large number of network parameters and incurs a significant computational cost. We introduce coupled EDNN (C-EDNN) to solve systems of PDEs by using independent networks for each state variable, which are only coupled through the governing equations. We also introduce distributed EDNN (D-EDNN) by spatially partitioning the global domain into several elements and assigning individual EDNNs to each element to solve the local evolution of the PDE. The networks then exchange the solution and fluxes at their interfaces, similar to flux-reconstruction methods, and ensure that the PDE dynamics are accurately preserved between neighboring elements. Together C-EDNN and D-EDNN form the general class of Multi-EDNN methods. We demonstrate these methods with aid of canonical problems including linear advection, the heat equation, and the compressible Navier-Stokes equations in Couette and Taylor-Green flows., Comment: 22 pages, 8 figures

Coordinating communication and control is a key component in the stability and performance of networked multi-agent systems. While single user networked control systems have gained a lot of attention within this domain, in this work, we address the more challenging problem of large population multi-team dynamic games. In particular, each team constitutes two decision makers (namely, the sensor and the controller) who coordinate over a shared network to control a dynamically evolving state of interest under costs on both actuation and sensing/communication. Due to the shared nature of the wireless channel, the overall cost of each team depends on other teams' policies, thereby leading to a noncooperative game setup. Due to the presence of a large number of teams, we compute approximate decentralized Nash equilibrium policies for each team using the paradigm of (extended) mean-field games, which is governed by (1) the mean traffic flowing over the channel, and (2) the value of information at the sensor, which highlights the semantic nature of the ensuing communication. In the process, we compute optimal controller policies and approximately optimal sensor policies for each representative team of the mean-field system to alleviate the problem of general non-contractivity of the mean-field fixed point operator associated with the finite cardinality of the sensor action space. Consequently, we also prove the $\epsilon$--Nash property of the mean-field equilibrium solution which essentially characterizes how well the solution derived using mean-field analysis performs on the finite-team system. Finally, we provide extensive numerical simulations, which corroborate the theoretical findings and lead to additional insights on the properties of the results presented., Comment: Submitted to IEEE for possible publication

In task-oriented conversational AI evaluation, unsupervised methods poorly correlate with human judgments, and supervised approaches lack generalization. Recent advances in large language models (LLMs) show robust zeroshot and few-shot capabilities across NLP tasks. This paper explores using LLMs for automated dialogue quality evaluation, experimenting with various configurations on public and proprietary datasets. Manipulating factors such as model size, in-context examples, and selection techniques, we examine "chain-of-thought" (CoT) reasoning and label extraction procedures. Our results show that (1) larger models yield more accurate dialogue labels; (2) algorithmic selection of in-context examples outperforms random selection; (3) CoT reasoning where an LLM is asked to provide justifications before outputting final labels improves performance; and (4) fine-tuned LLMs outperform out-of-the-box ones. Our results indicate that LLMs that are suitably fine-tuned and have sufficient reasoning capabilities can be leveraged for automated dialogue evaluation.

In this paper, we study the problem of robust cooperative multi-agent reinforcement learning (RL) where a large number of cooperative agents with distributed information aim to learn policies in the presence of \emph{stochastic} and \emph{non-stochastic} uncertainties whose distributions are respectively known and unknown. Focusing on policy optimization that accounts for both types of uncertainties, we formulate the problem in a worst-case (minimax) framework, which is is intractable in general. Thus, we focus on the Linear Quadratic setting to derive benchmark solutions. First, since no standard theory exists for this problem due to the distributed information structure, we utilize the Mean-Field Type Game (MFTG) paradigm to establish guarantees on the solution quality in the sense of achieved Nash equilibrium of the MFTG. This in turn allows us to compare the performance against the corresponding original robust multi-agent control problem. Then, we propose a Receding-horizon Gradient Descent Ascent RL algorithm to find the MFTG Nash equilibrium and we prove a non-asymptotic rate of convergence. Finally, we provide numerical experiments to demonstrate the efficacy of our approach relative to a baseline algorithm., Comment: Accepted for publication in L4DC 2024

The objective of this research is to introduce a network specialized in predicting drugs that can be repurposed by investigating real-world evidence sources, such as clinical trials and biomedical literature. Specifically, it aims to generate drug combination therapies for complex diseases (e.g., cancer, Alzheimer's). We present a multilayered network medicine approach, empowered by a highly configured ChatGPT prompt engineering system, which is constructed on the fly to extract drug mentions in clinical trials. Additionally, we introduce a novel algorithm that connects real-world evidence with disease-specific signaling pathways (e.g., KEGG database). This sheds light on the repurposability of drugs if they are found to bind with one or more protein constituents of a signaling pathway. To demonstrate, we instantiated the framework for breast cancer and found that, out of 46 breast cancer signaling pathways, the framework identified 38 pathways that were covered by at least two drugs. This evidence signals the potential for combining those drugs. Specifically, the most covered signaling pathway, ID hsa:2064, was covered by 108 drugs, some of which can be combined. Conversely, the signaling pathway ID hsa:1499 was covered by only two drugs, indicating a significant gap for further research. Our network medicine framework, empowered by GenAI, shows promise in identifying drug combinations with a high degree of specificity, knowing the exact signaling pathways and proteins that serve as targets. It is noteworthy that ChatGPT successfully accelerated the process of identifying drug mentions in clinical trials, though further investigations are required to determine the relationships among the drug mentions., Comment: 9 pages double columns, 5 figures, 3 algorithms, 3 tables, and 1 listing, Submitted to IEEE MedAI'24 Conference, to be held November 15-17, Chongqing, China

Quantum Annealing (QA) holds great potential for solving combinatorial optimization problems efficiently. However, the effectiveness of QA algorithms heavily relies on the embedding of problem instances, represented as logical graphs, into the quantum unit processing (QPU) whose topology is in form of a limited connectivity graph, known as the minor embedding Problem. Existing methods for the minor embedding problem suffer from scalability issues when confronted with larger problem sizes. In this paper, we propose a novel approach utilizing Reinforcement Learning (RL) techniques to address the minor embedding problem, named CHARME. CHARME includes three key components: a Graph Neural Network (GNN) architecture for policy modeling, a state transition algorithm ensuring solution validity, and an order exploration strategy for effective training. Through comprehensive experiments on synthetic and real-world instances, we demonstrate that the efficiency of our proposed order exploration strategy as well as our proposed RL framework, CHARME. In details, CHARME yields superior solutions compared to fast embedding methods such as Minorminer and ATOM. Moreover, our method surpasses the OCT-based approach, known for its slower runtime but high-quality solutions, in several cases. In addition, our proposed exploration enhances the efficiency of the training of the CHARME framework by providing better solutions compared to the greedy strategy.

We study index-based processing for connectivity queries within sliding windows on streaming graphs. These queries, which determine whether two vertices belong to the same connected component, are fundamental operations in real-time graph data processing and demand high throughput and low latency. While indexing methods that leverage data structures for fully dynamic connectivity can facilitate efficient query processing, they encounter significant challenges with deleting expired edges from the window during window updates. We introduce a novel indexing approach that eliminates the need for physically performing edge deletions. This is achieved through a unique bidirectional incremental computation framework, referred to as the BIC model. The BIC model implements two distinct incremental computations to compute connected components within the window, operating along and against the timeline, respectively. These computations are then merged to efficiently compute queries in the window. We propose techniques for optimized index storage, incremental index updates, and efficient query processing to improve BIC effectiveness. Empirically, BIC achieves a 14$\times$ increase in throughput and a reduction in P95 latency by up to 3900$\times$ when compared to state-of-the-art indexes., Comment: To appear in VLDB 2024

Federated learning is a machine learning approach where multiple devices collaboratively learn with the help of a parameter server by sharing only their local updates. While gradient-based optimization techniques are widely adopted in this domain, the curvature information that second-order methods exhibit is crucial to guide and speed up the convergence. This paper introduces a scalable second-order method, allowing the adoption of curvature information in federated large models. Our method, coined Fed-Sophia, combines a weighted moving average of the gradient with a clipping operation to find the descent direction. In addition to that, a lightweight estimation of the Hessian's diagonal is used to incorporate the curvature information. Numerical evaluation shows the superiority, robustness, and scalability of the proposed Fed-Sophia scheme compared to first and second-order baselines., Comment: ICC 2024

In this paper, we revisit the two-player continuous-time infinite-horizon linear quadratic differential game problem, where one of the players can sample the state of the system only intermittently due to a sensing constraint while the other player can do so continuously. Under these asymmetric sensing limitations between the players, we analyze the optimal sensing and control strategies for the player at a disadvantage while the other player continues to play its security strategy. We derive an optimal sensor policy within the class of stationary randomized policies. Finally, using simulations, we show that the expected cost accrued by the first player approaches its security level as its sensing limitation is relaxed., Comment: Accepted to IEEE L-CSS

In the effort to learn from extensive collections of distributed data, federated learning has emerged as a promising approach for preserving privacy by using a gradient-sharing mechanism instead of exchanging raw data. However, recent studies show that private training data can be leaked through many gradient attacks. While previous analytical-based attacks have successfully reconstructed input data from fully connected layers, their effectiveness diminishes when applied to convolutional layers. This paper introduces an advanced data leakage method to efficiently exploit convolutional layers' gradients. We present a surprising finding: even with non-fully invertible activation functions, such as ReLU, we can analytically reconstruct training samples from the gradients. To the best of our knowledge, this is the first analytical approach that successfully reconstructs convolutional layer inputs directly from the gradients, bypassing the need to reconstruct layers' outputs. Prior research has mainly concentrated on the weight constraints of convolution layers, overlooking the significance of gradient constraints. Our findings demonstrate that existing analytical methods used to estimate the risk of gradient attacks lack accuracy. In some layers, attacks can be launched with less than 5% of the reported constraints.

This paper introduces a new method to achieve stable convergence to Nash equilibrium in duopoly noncooperative games. Inspired by the recent fixed-time Nash Equilibrium seeking (NES) as well as prescribed-time extremum seeking (ES) and source seeking schemes, our approach employs a distributed sliding mode control (SMC) scheme, integrating extremum seeking with sinusoidal perturbation signals to estimate the pseudogradients of quadratic payoff functions. Notably, this is the first attempt to address noncooperative games without relying on models, combining classical extremum seeking with relay components instead of proportional control laws. We prove finite-time convergence of the closed-loop average system to Nash equilibrium using stability analysis techniques such as time-scaling, Lyapunov's direct method, and averaging theory for discontinuous systems. Additionally, we quantify the size of residual sets around the Nash equilibrium and validate our theoretical results through simulations., Comment: 8 pages and 2 figures. arXiv admin note: substantial text overlap with arXiv:2404.07287

Automated Essay Scoring automates the grading process of essays, providing a great advantage for improving the writing proficiency of students. While holistic essay scoring research is prevalent, a noticeable gap exists in scoring essays for specific quality traits. In this work, we focus on the relevance trait, which measures the ability of the student to stay on-topic throughout the entire essay. We propose a novel approach for graded relevance scoring of written essays that employs dense retrieval encoders. Dense representations of essays at different relevance levels then form clusters in the embeddings space, such that their centroids are potentially separate enough to effectively represent their relevance levels. We hence use the simple 1-Nearest-Neighbor classification over those centroids to determine the relevance level of an unseen essay. As an effective unsupervised dense encoder, we leverage Contriever, which is pre-trained with contrastive learning and demonstrated comparable performance to supervised dense retrieval models. We tested our approach on both task-specific (i.e., training and testing on same task) and cross-task (i.e., testing on unseen task) scenarios using the widely used ASAP++ dataset. Our method establishes a new state-of-the-art performance in the task-specific scenario, while its extension for the cross-task scenario exhibited a performance that is on par with the state-of-the-art model for that scenario. We also analyzed the performance of our approach in a more practical few-shot scenario, showing that it can significantly reduce the labeling cost while sacrificing only 10% of its effectiveness., Comment: Accepted at SIGIR 2024

Deep Learning (DL) is rapidly maturing to the point that it can be used in safety- and security-crucial applications. However, adversarial samples, which are undetectable to the human eye, pose a serious threat that can cause the model to misbehave and compromise the performance of such applications. Addressing the robustness of DL models has become crucial to understanding and defending against adversarial attacks. In this study, we perform comprehensive experiments to examine the effect of adversarial attacks and defenses on various model architectures across well-known datasets. Our research focuses on black-box attacks such as SimBA, HopSkipJump, MGAAttack, and boundary attacks, as well as preprocessor-based defensive mechanisms, including bits squeezing, median smoothing, and JPEG filter. Experimenting with various models, our results demonstrate that the level of noise needed for the attack increases as the number of layers increases. Moreover, the attack success rate decreases as the number of layers increases. This indicates that model complexity and robustness have a significant relationship. Investigating the diversity and robustness relationship, our experiments with diverse models show that having a large number of parameters does not imply higher robustness. Our experiments extend to show the effects of the training dataset on model robustness. Using various datasets such as ImageNet-1000, CIFAR-100, and CIFAR-10 are used to evaluate the black-box attacks. Considering the multiple dimensions of our analysis, e.g., model complexity and training dataset, we examined the behavior of black-box attacks when models apply defenses. Our results show that applying defense strategies can significantly reduce attack effectiveness. This research provides in-depth analysis and insight into the robustness of DL models against various attacks, and defenses.

Rapid advancements of deep learning are accelerating adoption in a wide variety of applications, including safety-critical applications such as self-driving vehicles, drones, robots, and surveillance systems. These advancements include applying variations of sophisticated techniques that improve the performance of models. However, such models are not immune to adversarial manipulations, which can cause the system to misbehave and remain unnoticed by experts. The frequency of modifications to existing deep learning models necessitates thorough analysis to determine the impact on models' robustness. In this work, we present an experimental evaluation of the effects of model modifications on deep learning model robustness using adversarial attacks. Our methodology involves examining the robustness of variations of models against various adversarial attacks. By conducting our experiments, we aim to shed light on the critical issue of maintaining the reliability and safety of deep learning models in safety- and security-critical applications. Our results indicate the pressing demand for an in-depth assessment of the effects of model changes on the robustness of models.

We consider a communication system where a group of users, interconnected in a bidirectional gossip network, wishes to follow a time-varying source, e.g., updates on an event, in real-time. The users wish to maintain their expected version ages below a threshold, and can either rely on gossip from their neighbors or directly subscribe to a server publishing about the event, if the former option does not meet the timeliness requirements. The server wishes to maximize its profit by increasing subscriptions from users and minimizing event sampling frequency to reduce costs. This leads to a Stackelberg game between the server and the users where the sender is the leader deciding its sampling frequency and the users are the followers deciding their subscription strategies. We investigate equilibrium strategies for low-connectivity and high-connectivity topologies.

We consider a communication system consisting of a server that tracks and publishes updates about a time-varying data source or event, and a gossip network of users interested in closely tracking the event. The timeliness of the information is measured through the version age of information. The users wish to have their expected version ages remain below a threshold, and have the option to either rely on gossip from their neighbors or subscribe to the server directly to follow updates about the event if the former option does not meet the timeliness requirements. The server wishes to maximize its profit by increasing the number of subscribers and reducing costs associated with the frequent sampling of the event. We model the problem setup as a Stackelberg game between the server and the users, where the server commits to a frequency of sampling the event, and the users make decisions on whether to subscribe or not. As an initial work, we focus on directed networks with unidirectional flow of information and obtain the optimal equilibrium strategies for all the players. We provide simulation results to confirm the theoretical findings and provide additional insights.

Given a training set in the form of a paired $(\mathcal{X},\mathcal{Y})$, we say that the control system $\dot x = f(x,u)$ has learned the paired set via the control $u^*$ if the system steers each point of $\mathcal{X}$ to its corresponding target in $\mathcal{Y}$. If the training set is expanded, most existing methods for finding a new control $u^*$ require starting from scratch, resulting in a quadratic increase in complexity with the number of points. To overcome this limitation, we introduce the concept of $\textit{ tuning without forgetting}$. We develop $\textit{an iterative algorithm}$ to tune the control $u^*$ when the training set expands, whereby points already in the paired set are still matched, and new training samples are learned. At each update of our method, the control $u^*$ is projected onto the kernel of the end-point mapping generated by the controlled dynamics at the learned samples. It ensures keeping the end-points for the previously learned samples constant while iteratively learning additional samples.

Large language models (LLMs) have been driving a new wave of interactive AI applications across numerous domains. However, efficiently serving LLM inference requests is challenging due to their unpredictable execution times originating from the autoregressive nature of generative models. Existing LLM serving systems exploit first-come-first-serve (FCFS) scheduling, suffering from head-of-line blocking issues. To address the non-deterministic nature of LLMs and enable efficient interactive LLM serving, we present a speculative shortest-job-first (SSJF) scheduler that uses a light proxy model to predict LLM output sequence lengths. Our open-source SSJF implementation does not require changes to memory management or batching strategies. Evaluations on real-world datasets and production workload traces show that SSJF reduces average job completion times by 30.5-39.6% and increases throughput by 2.2-3.6x compared to FCFS schedulers, across no batching, dynamic batching, and continuous batching settings., Comment: Accepted at AIOps'24

This paper proposes a novel approach for locally stable convergence to Nash equilibrium in duopoly noncooperative games based on a distributed event-triggered control scheme. The proposed approach employs extremum seeking, with sinusoidal perturbation signals applied to estimate the Gradient (first derivative) of unknown quadratic payoff functions. This is the first instance of noncooperative games being tackled in a model-free fashion integrated with the event-triggered methodology. Each player evaluates independently the deviation between the corresponding current state variable and its last broadcasted value to update the player action, while they preserve control performance under limited bandwidth of the actuation paths and still guarantee stability for the closed-loop dynamics. In particular, the stability analysis is carried out using time-scaling technique, Lyapunov's direct method and averaging theory for discontinuous systems. We quantify the size of the ultimate small residual sets around the Nash equilibrium and illustrate the theoretical results numerically on an example.