Search

Classical parameter-space Bayesian inference for Bayesian neural networks (BNNs) suffers from several unresolved prior issues, such as knowledge encoding intractability and pathological behaviours in deep networks, which can lead to improper posterior inference. To address these issues, functional Bayesian inference has recently been proposed leveraging functional priors, such as the emerging functional variational inference. In addition to variational methods, stochastic gradient Markov Chain Monte Carlo (MCMC) is another scalable and effective inference method for BNNs to asymptotically generate samples from the true posterior by simulating continuous dynamics. However, existing MCMC methods perform solely in parameter space and inherit the unresolved prior issues, while extending these dynamics to function space is a non-trivial undertaking. In this paper, we introduce novel functional MCMC schemes, including stochastic gradient versions, based on newly designed diffusion dynamics that can incorporate more informative functional priors. Moreover, we prove that the stationary measure of these functional dynamics is the target posterior over functions. Our functional MCMC schemes demonstrate improved performance in both predictive accuracy and uncertainty quantification on several tasks compared to naive parameter-space MCMC and functional variational inference.

Realization of quantum computing requires the development of high-fidelity quantum gates that are resilient to decoherence, control errors, and environmental noise. While non-adiabatic holonomic quantum computation (NHQC) offers a promising approach, it often necessitates system-specific adjustments. This work presents a versatile scheme for implementing NHQC gates across multiple qubit systems by optimizing multiple degrees of freedom using a genetic algorithm. The scheme is applied to three qubit systems: ensemble rare-earth ion (REI) qubits, single REI qubits, and superconducting transmon qubits. Numerical simulations demonstrate that the optimized gate operations are robust against frequency detuning and induce low off-resonant excitations, making the scheme effective for advancing fault-tolerant quantum computation across various platforms., Comment: 20 pages, 11 figures, Journal of the Optical Society of America B

Inspired by the great progress in the observations of charmonium-like states in recent years, we perform a systematic analysis about the ground states and the first radially excited states of $qc\bar{q}\bar{c}$ ($q$=$u/d$ and $s$) tetraquark systems. Their mass spectra, root mean square (r.m.s.) radii and radial density distributions are predicted within the framework of relativized quark model. By comparing with experimental data, some potential candidates for hidden-charm tetraquark states are suggested. For $qc\bar{q}\bar{c}$ ($q$=$u/d$) system, if $Z_{c}(3900)$ is supposed to be a compact tetraquark state with $J^{PC}=1^{+-}$, $Z(4430)$ can be interpreted as the first radially excited states of $Z_{c}(3900)$. Another broad structure $Z_{c}(4200)$ can also be explained as a partner of $Z_{c}(3900)$, and it arise from a higher state with $J^{PC}=1^{+-}$. In addition, theoretical predictions indicate that the possible assignments for $X(3930)$, $X(4050)$ and $X(4250)$ are low lying $0^{++}$ tetraquark states. As for the $sc\bar{s}\bar{c}$ system, $X(4140)$ and $X(4274)$ structures can be interpreted as this type of tetraquark states with $J^{PC}=1^{++}$, and $X(4350)$ can be described as a $sc\bar{s}\bar{c}$ tetraquark with $J^{PC}=0^{++}$. With regard to $qc\bar{s}\bar{c}$ ($q$=$u/d$) system, we find two potential candidates for this type of tetraquark, which are $Z_{cs}(4000)$ and $Z_{cs}(4220)$ structures. The measured masses of these two structures are in agreement with theoretical predictions for the $1^{+}$ state.

Solving large-scale robust portfolio optimization problems is challenging due to the high computational demands associated with an increasing number of assets, the amount of data considered, and market uncertainty. To address this issue, we propose an extended supporting hyperplane approximation approach for efficiently solving a class of distributionally robust portfolio problems for a general class of additively separable utility functions and polyhedral ambiguity distribution set, applied to a large-scale set of assets. Our technique is validated using a large-scale portfolio of the S&P 500 index constituents, demonstrating robust out-of-sample trading performance. More importantly, our empirical studies show that this approach significantly reduces computational time compared to traditional concave Expected Log-Growth (ELG) optimization, with running times decreasing from several thousand seconds to just a few. This method provides a scalable and practical solution to large-scale robust portfolio optimization, addressing both theoretical and practical challenges., Comment: Submitted to possible publication

Cross-Domain Recommendation (CDR) is a promising paradigm inspired by transfer learning to solve the cold-start problem in recommender systems. Existing state-of-the-art CDR methods train an explicit mapping function to transfer the cold-start users from a data-rich source domain to a target domain. However, a limitation of these methods is that the mapping function is trained on overlapping users across domains, while only a small number of overlapping users are available for training. By visualizing the loss landscape of the existing CDR model, we find that training on a small number of overlapping users causes the model to converge to sharp minima, leading to poor generalization. Based on this observation, we leverage loss-geometry-based machine learning approach and propose a novel CDR method called Sharpness-Aware CDR (SCDR). Our proposed method simultaneously optimizes recommendation loss and loss sharpness, leading to better generalization with theoretical guarantees. Empirical studies on real-world datasets demonstrate that SCDR significantly outperforms the other CDR models for cold-start recommendation tasks, while concurrently enhancing the model's robustness to adversarial attacks.

In this work, lateral displacements of transmitted and reflected spin waves at a 360 degree domain wall (360DW), which is referred to as the spin-wave Goos-H\"{a}nchen effect (SWGHE), are systematically investigated in magnetic heterostructures with perpendicular easy/hard axis and wall-extension direction. Similar to the counterpart at heterochiral interfaces, the interfacial Dzyaloshinskii-Moriya interactions (IDMI) originating from a heavy-metal substrate is important for the emergence of SWGHE. More interestingly, the SWGHE can even survive in ferromagnets with biaxial anisotropy (either intrinsic or caused by shape anisotropy) in the absence of IDMI due to the unique 360DW-induced potentials which are distinct to the well-known P\"{o}schl-Teller ones. Numerics shows that these lateral displacements are generally fractions of the spin-wave wavelength. They can be further enhanced by an array of well-separated 360DWs thus provide a large variety for spin-wave manipulation., Comment: 10 pages, 4 figures

Artificial Intelligence (AI) has emerged as a key driver of precision agriculture, facilitating enhanced crop productivity, optimized resource use, farm sustainability, and informed decision-making. Also, the expansion of genome sequencing technology has greatly increased crop genomic resources, deepening our understanding of genetic variation and enhancing desirable crop traits to optimize performance in various environments. There is increasing interest in using machine learning (ML) and deep learning (DL) algorithms for genotype-to-phenotype prediction due to their excellence in capturing complex interactions within large, high-dimensional datasets. In this work, we propose a new LSTM autoencoder-based model for barley genotype-to-phenotype prediction, specifically for flowering time and grain yield estimation, which could potentially help optimize yields and management practices. Our model outperformed the other baseline methods, demonstrating its potential in handling complex high-dimensional agricultural datasets and enhancing crop phenotype prediction performance.

Many realistic decision-making problems in networked scenarios, such as formation control and collaborative task offloading, often involve complicatedly entangled local decisions, which, however, have not been sufficiently investigated yet. Motivated by this, we study a class of decentralized optimization problems with a variable coupling structure that is new to the literature. Specifically, we consider a network of nodes collaborating to minimize a global objective subject to a collection of global inequality and equality constraints, which are formed by the local objective and constraint functions of the nodes. On top of that, we allow such local functions of each node to depend on not only its own decision variable but the decisions of its neighbors as well. To address this problem, we propose a decentralized projected primal-dual algorithm. It first incorporates a virtual-queue technique with a primal-dual-primal scheme, and then linearizes the non-separable objective and constraint functions to enable decentralized implementation. Under mild conditions, we derive $O(1/k)$ convergence rates for both objective error and constraint violations. Finally, two numerical experiments corroborate our theoretical results and illustrate the competitive performance of the proposed algorithm.

This paper considers a consensus optimization problem, where all the nodes in a network, with access to the zeroth-order information of its local objective function only, attempt to cooperatively achieve a common minimizer of the sum of their local objectives. To address this problem, we develop ZoPro, a zeroth-order proximal algorithm, which incorporates a zeroth-order oracle for approximating Hessian and gradient into a recently proposed, high-performance distributed second-order proximal algorithm. We show that the proposed ZoPro algorithm, equipped with a dynamic stepsize, converges linearly to a neighborhood of the optimum in expectation, provided that each local objective function is strongly convex and smooth. Extensive simulations demonstrate that ZoPro converges faster than several state-of-the-art distributed zeroth-order algorithms and outperforms a few distributed second-order algorithms in terms of running time for reaching given accuracy., Comment: 8 pages, 3 figures

The form factors of $B_c\rightarrow\eta_c$ and $B_c\rightarrow J/\psi$ are analyzed in the framework of three-point QCD sum rules. In these analyses, the contributions of the vacuum condensate terms $\langle g_{s}^{2}GG\rangle$ and $\langle g_{s}^{3}GGGf\rangle$ are considered. In addition, the decay widths and branching ratios of several decay channels are obtained by using the calculated form factors. These decay processes include the nonleptonic decays of $B_c^- \to \eta_c \pi^-$, $\eta_c K^-$, $\eta_c \rho^-$, $\eta_c K^{*-}$, $B_c^- \to J/\psi \pi^-$, $J/\psi K^-$, $J/\psi \rho^-$, $J/\psi K^{*-}$, and the semileptonic decays of $B_c^- \to \eta_c \mathcal{l} \bar{\nu}$, $B_c^- \to J/\psi \mathcal{l} \bar{\nu}$. These results about the form factors and decay properties of $B_c$ meson provide useful information for us to study the heavy-quark dynamics and find new physics(NP) beyond Standard Model(SM).

AI-aided clinical diagnosis is desired in medical care. Existing deep learning models lack explainability and mainly focus on image analysis. The recently developed Dynamic Uncertain Causality Graph (DUCG) approach is causality-driven, explainable, and invariant across different application scenarios, without problems of data collection, labeling, fitting, privacy, bias, generalization, high cost and high energy consumption. Through close collaboration between clinical experts and DUCG technicians, 46 DUCG models covering 54 chief complaints were constructed. Over 1,000 diseases can be diagnosed without triage. Before being applied in real-world, the 46 DUCG models were retrospectively verified by third-party hospitals. The verified diagnostic precisions were no less than 95%, in which the diagnostic precision for every disease including uncommon ones was no less than 80%. After verifications, the 46 DUCG models were applied in the real-world in China. Over one million real diagnosis cases have been performed, with only 17 incorrect diagnoses identified. Due to DUCG's transparency, the mistakes causing the incorrect diagnoses were found and corrected. The diagnostic abilities of the clinicians who applied DUCG frequently were improved significantly. Following the introduction to the earlier presented DUCG methodology, the recommendation algorithm for potential medical checks is presented and the key idea of DUCG is extracted.

With the development of Large Language Models (LLMs), social biases in the LLMs have become a crucial issue. While various benchmarks for social biases have been provided across languages, the extent to which Japanese LLMs exhibit social biases has not been fully investigated. In this study, we construct the Japanese Bias Benchmark dataset for Question Answering (JBBQ) based on the English bias benchmark BBQ, and analyze social biases in Japanese LLMs. The results show that while current open Japanese LLMs improve their accuracies on JBBQ by setting larger parameters, their bias scores become larger. In addition, prompts with warnings about social biases and Chain-of-Thought prompting reduce the effect of biases in model outputs, but there is room for improvement in the consistency of reasoning.

Deep reinforcement learning is used in various domains, but usually under the assumption that the environment has stationary conditions like transitions and state distributions. When this assumption is not met, performance suffers. For this reason, tracking continuous environmental changes and adapting to unpredictable conditions is challenging yet crucial because it ensures that systems remain reliable and flexible in practical scenarios. Our research introduces Behavior-Aware Detection and Adaptation (BADA), an innovative framework that merges environmental change detection with behavior adaptation. The key inspiration behind our method is that policies exhibit different global behaviors in changing environments. Specifically, environmental changes are identified by analyzing variations between behaviors using Wasserstein distances without manually set thresholds. The model adapts to the new environment through behavior regularization based on the extent of changes. The results of a series of experiments demonstrate better performance relative to several current algorithms. This research also indicates significant potential for tackling this long-standing challenge., Comment: Accepted by IJCAI 2024

Uncertain changes in data streams present challenges for machine learning models to dynamically adapt and uphold performance in real-time. Particularly, classification boundary change, also known as real concept drift, is the major cause of classification performance deterioration. However, accurately detecting real concept drift remains challenging because the theoretical foundations of existing drift detection methods - two-sample distribution tests and monitoring classification error rate, both suffer from inherent limitations such as the inability to distinguish virtual drift (changes not affecting the classification boundary, will introduce unnecessary model maintenance), limited statistical power, or high computational cost. Furthermore, no existing detection method can provide information on the trend of the drift, which could be invaluable for model maintenance. This work presents a novel real concept drift detection method based on Neighbor-Searching Discrepancy, a new statistic that measures the classification boundary difference between two samples. The proposed method is able to detect real concept drift with high accuracy while ignoring virtual drift. It can also indicate the direction of the classification boundary change by identifying the invasion or retreat of a certain class, which is also an indicator of separability change between classes. A comprehensive evaluation of 11 experiments is conducted, including empirical verification of the proposed theory using artificial datasets, and experimental comparisons with commonly used drift handling methods on real-world datasets. The results show that the proposed theory is robust against a range of distributions and dimensions, and the drift detection method outperforms state-of-the-art alternative methods.

Multi-modal Large Language Models (MLLMs) frequently face challenges from concept drift when dealing with real-world streaming data, wherein distributions change unpredictably. This mainly includes gradual drift due to long-tailed data and sudden drift from Out-Of-Distribution (OOD) data, both of which have increasingly drawn the attention of the research community. While these issues have been extensively studied in the individual domain of vision or language, their impacts on MLLMs in concept drift settings remain largely underexplored. In this paper, we reveal the susceptibility and vulnerability of Vision-Language (VL) models to significant biases arising from gradual drift and sudden drift, particularly in the pre-training. To effectively address these challenges, we propose a unified framework that extends concept drift theory to the multi-modal domain, enhancing the adaptability of the VL model to the distribution unpredictable changes. Additionally, a T-distribution based drift adapter is proposed to effectively mitigate the bias induced by the gradual drift, which also facilitates the model in distinguishing sudden distribution changes through explicit distribution modeling. Extensive experiments demonstrate our method enhances the efficiency and accuracy of image-text alignment in the pre-training of VL models, particularly in the concept drift scenario. Moreover, various downstream tasks exhibit significant improvements in our model's ability to adapt to long-tailed open world. Furthermore, we create a set of multi-modal datasets called OpenMMlo, specifically tailored for the long-tailed open world settings, to validate our findings. To foster the development of the multi-modal community, we have made both OpenMMlo datasets and our code publicly available at: https://github.com/Anonymous0Knight/ConceptDriftMLLMs., Comment: 13 pages

Shifting the focus from principles to practical implementation, responsible artificial intelligence (AI) has garnered considerable attention across academia, industry, and society at large. Despite being in its nascent stages, this emerging field grapples with nebulous concepts and intricate knowledge frameworks. By analyzing three prevailing concepts - explainable AI, trustworthy AI, and ethical AI, this study defined responsible AI and identified its core principles. Methodologically, this study successfully demonstrated the implementation of leveraging AI's capabilities into bibliometrics for enhanced knowledge discovery and the cross-validation of experimentally examined models with domain insights. Empirically, this study investigated 17,799 research articles contributed by the AI community since 2015. This involves recognizing key technological players and their relationships, unveiling the topical landscape and hierarchy of responsible AI, charting its evolution, and elucidating the interplay between the responsibility principles and primary AI techniques. An analysis of a core cohort comprising 380 articles from multiple disciplines captures the most recent advancements in responsible AI. As one of the pioneering bibliometric studies dedicated to exploring responsible AI, this study will provide comprehensive macro-level insights, enhancing the understanding of responsible AI while furnishing valuable knowledge support for AI regulation and governance initiatives., Comment: 14 pages, 9 figures

Cooperative Multi-Agent Reinforcement Learning (MARL) necessitates seamless collaboration among agents, often represented by an underlying relation graph. Existing methods for learning this graph primarily focus on agent-pair relations, neglecting higher-order relationships. While several approaches attempt to extend cooperation modelling to encompass behaviour similarities within groups, they commonly fall short in concurrently learning the latent graph, thereby constraining the information exchange among partially observed agents. To overcome these limitations, we present a novel approach to infer the Group-Aware Coordination Graph (GACG), which is designed to capture both the cooperation between agent pairs based on current observations and group-level dependencies from behaviour patterns observed across trajectories. This graph is further used in graph convolution for information exchange between agents during decision-making. To further ensure behavioural consistency among agents within the same group, we introduce a group distance loss, which promotes group cohesion and encourages specialization between groups. Our evaluations, conducted on StarCraft II micromanagement tasks, demonstrate GACG's superior performance. An ablation study further provides experimental evidence of the effectiveness of each component of our method., Comment: Accepted by IJCAI 2024

Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studied a more realistic setting: out-of-distribution (OOD) detection, where test data may come from classes that are unknown during training (i.e., OOD data). Due to the unavailability and diversity of OOD data, good generalization ability is crucial for effective OOD detection algorithms, and corresponding learning theory is still an open problem. To study the generalization of OOD detection, this paper investigates the probably approximately correct (PAC) learning theory of OOD detection that fits the commonly used evaluation metrics in the literature. First, we find a necessary condition for the learnability of OOD detection. Then, using this condition, we prove several impossibility theorems for the learnability of OOD detection under some scenarios. Although the impossibility theorems are frustrating, we find that some conditions of these impossibility theorems may not hold in some practical scenarios. Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios. Lastly, we offer theoretical support for representative OOD detection works based on our OOD theory., Comment: Accepted by JMLR in 7th of April, 2024. This is a journal extension of the previous NeurIPS 2022 Outstanding Paper "Is Out-of-distribution Detection Learnable?" [arXiv:2210.14707]

The Large Language Model (LLM) is widely employed for tasks such as intelligent assistants, text summarization, translation, and multi-modality on mobile phones. However, the current methods for on-device LLM deployment maintain slow inference speed, which causes poor user experience. To facilitate high-efficiency LLM deployment on device GPUs, we propose four optimization techniques: (a) a symbolic expression-based approach to support dynamic shape model inference; (b) operator optimizations and execution priority setting to enhance inference speed and reduce phone lagging; (c) an FP4 quantization method termed M0E4 to reduce dequantization overhead; (d) a sub-tensor-based technique to eliminate the need for copying KV cache after LLM inference. Furthermore, we implement these methods in our mobile inference engine, Transformer-Lite, which is compatible with both Qualcomm and MTK processors. We evaluated Transformer-Lite's performance using LLMs with varied architectures and parameters ranging from 2B to 14B. Specifically, we achieved prefill and decoding speeds of 121 token/s and 14 token/s for ChatGLM2 6B, and 330 token/s and 30 token/s for smaller Gemma 2B, respectively. Compared with CPU-based FastLLM and GPU-based MLC-LLM, our engine attains over 10x speedup for the prefill speed and 2~3x speedup for the decoding speed., Comment: 21 pages, 6 figures, fix "E0M4" spell mistake, fix FLOPS to TFLOPS

Effective agent coordination is crucial in cooperative Multi-Agent Reinforcement Learning (MARL). While agent cooperation can be represented by graph structures, prevailing graph learning methods in MARL are limited. They rely solely on one-step observations, neglecting crucial historical experiences, leading to deficient graphs that foster redundant or detrimental information exchanges. Additionally, high computational demands for action-pair calculations in dense graphs impede scalability. To address these challenges, we propose inferring a Latent Temporal Sparse Coordination Graph (LTS-CG) for MARL. The LTS-CG leverages agents' historical observations to calculate an agent-pair probability matrix, where a sparse graph is sampled from and used for knowledge exchange between agents, thereby simultaneously capturing agent dependencies and relation uncertainty. The computational complexity of this procedure is only related to the number of agents. This graph learning process is further augmented by two innovative characteristics: Predict-Future, which enables agents to foresee upcoming observations, and Infer-Present, ensuring a thorough grasp of the environmental context from limited data. These features allow LTS-CG to construct temporal graphs from historical and real-time information, promoting knowledge exchange during policy learning and effective collaboration. Graph learning and agent training occur simultaneously in an end-to-end manner. Our demonstrated results on the StarCraft II benchmark underscore LTS-CG's superior performance.

Graph neural networks (GNNs) are a powerful solution for various structure learning applications due to their strong representation capabilities for graph data. However, traditional GNNs, relying on message-passing mechanisms that gather information exclusively from first-order neighbours (known as positive samples), can lead to issues such as over-smoothing and over-squashing. To mitigate these issues, we propose a layer-diverse negative sampling method for message-passing propagation. This method employs a sampling matrix within a determinantal point process, which transforms the candidate set into a space and selectively samples from this space to generate negative samples. To further enhance the diversity of the negative samples during each forward pass, we develop a space-squeezing method to achieve layer-wise diversity in multi-layer GNNs. Experiments on various real-world graph datasets demonstrate the effectiveness of our approach in improving the diversity of negative samples and overall learning performance. Moreover, adding negative samples dynamically changes the graph's topology, thus with the strong potential to improve the expressiveness of GNNs and reduce the risk of over-squashing., Comment: Published in Transactions on Machine Learning Research (03/2024)

In this article, we analyze the electromagnetic form factors of the vector heavy-light mesons to the pseudoscalar heavy-light mesons in the framework of three-point QCD sum rules, where the contributions of vacuum condensate terms $\langle\overline{q}q\rangle$, $\langle\overline{q}g_{s}\sigma Gq\rangle$, $\langle g_{s}^{2}G^{2}\rangle$, $\langle f^{3}G^{3}\rangle$ and $\langle\overline{q}q\rangle\langle g_{s}^{2}G^{2}\rangle$ are considered. With these results, we also obtain the radiative decay widths of the vector heavy-light mesons and then compare our results with those of other collaboration's. The final results about the radiative decay widths are $\Gamma(D^{*0}\to D^{0}\gamma)=1.74^{+0.40}_{-0.37}$ keV, $\Gamma(D^{*+}\to D^{+}\gamma)=0.17^{+0.08}_{-0.07}$ keV, $\Gamma(D_{s}^{*}\to D_{s}\gamma)=0.029^{+0.009}_{-0.008}$ keV, $\Gamma(B^{*0}\to B^{0}\gamma)=0.018^{+0.006}_{-0.005}$ keV, $\Gamma(B^{*+}\to B^{+}\gamma)=0.015^{+0.007}_{-0.007}$ keV and $\Gamma(B^{*}_{s}\to B_{s}\gamma)=0.016^{+0.003}_{-0.005}$ keV.

Multistream classification poses significant challenges due to the necessity for rapid adaptation in dynamic streaming processes with concept drift. Despite the growing research outcomes in this area, there has been a notable oversight regarding the temporal dynamic relationships between these streams, leading to the issue of negative transfer arising from irrelevant data. In this paper, we propose a novel Online Boosting Adaptive Learning (OBAL) method that effectively addresses this limitation by adaptively learning the dynamic correlation among different streams. Specifically, OBAL operates in a dual-phase mechanism, in the first of which we design an Adaptive COvariate Shift Adaptation (AdaCOSA) algorithm to construct an initialized ensemble model using archived data from various source streams, thus mitigating the covariate shift while learning the dynamic correlations via an adaptive re-weighting strategy. During the online process, we employ a Gaussian Mixture Model-based weighting mechanism, which is seamlessly integrated with the acquired correlations via AdaCOSA to effectively handle asynchronous drift. This approach significantly improves the predictive performance and stability of the target stream. We conduct comprehensive experiments on several synthetic and real-world data streams, encompassing various drifting scenarios and types. The results clearly demonstrate that OBAL achieves remarkable advancements in addressing multistream classification problems by effectively leveraging positive knowledge derived from multiple sources., Comment: AAAI 2024

In distributed optimization, the practical problem-solving performance is essentially sensitive to algorithm selection, parameter setting, problem type and data pattern. Thus, it is often laborious to acquire a highly efficient method for a given specific problem. In this paper, we propose a learning-based method to achieve efficient distributed optimization over networked systems. Specifically, a deep reinforcement learning (DRL) framework is developed for adaptive configuration within a parameterized unifying algorithmic form, which incorporates an abundance of decentralized first-order and second-order optimization algorithms. We exploit the local consensus and objective information to represent the regularities of problem instances and trace the solving progress, which constitute the states observed by a DRL agent. The framework is trained using Proximal Policy Optimization (PPO) on a number of practical problem instances of similar structures yet different problem data. Experiments on various smooth and non-smooth classes of objective functions demonstrate that our proposed learning-based method outperforms several state-of-the-art distributed optimization algorithms in terms of convergence speed and solution accuracy., Comment: 10 pages, 5 figures

This paper focuses on distributed constrained optimization over time-varying directed networks, where all agents cooperate to optimize the sum of their locally accessible objective functions subject to a coupled inequality constraint consisting of all their local constraint functions. To address this problem, we develop a buffering drift-plus-penalty algorithm, referred to as B-DPP. The proposed B-DPP algorithm utilizes the idea of drift-plus-penalty minimization in centralized optimization to control constraint violation and objective error, and adapts it to the distributed setting. It also innovatively incorporates a buffer variable into local virtual queue updates to acquire flexible and desirable tracking of constraint violation. We show that B-DPP achieves $O(1/\sqrt{t})$ rates of convergence to both optimality and feasibility, which outperform the alternative methods in the literature. Moreover, with a proper buffer parameter, B-DPP is capable of reaching feasibility within a finite number of iterations, which is a pioneering result in the area. Simulations on a resource allocation problem over 5G virtualized networks demonstrate the competitive convergence performance and efficiency of B-DPP.

Out-of-distribution (OOD) detection is crucial to modern deep learning applications by identifying and alerting about the OOD samples that should not be tested or used for making predictions. Current OOD detection methods have made significant progress when in-distribution (ID) and OOD samples are drawn from static distributions. However, this can be unrealistic when applied to real-world systems which often undergo continuous variations and shifts in ID and OOD distributions over time. Therefore, for an effective application in real-world systems, the development of OOD detection methods that can adapt to these dynamic and evolving distributions is essential. In this paper, we propose a novel and more realistic setting called continuously adaptive out-of-distribution (CAOOD) detection which targets on developing an OOD detection model that enables dynamic and quick adaptation to a new arriving distribution, with insufficient ID samples during deployment time. To address CAOOD, we develop meta OOD learning (MOL) by designing a learning-to-adapt diagram such that a good initialized OOD detection model is learned during the training process. In the testing process, MOL ensures OOD detection performance over shifting distributions by quickly adapting to new distributions with a few adaptations. Extensive experiments on several OOD benchmarks endorse the effectiveness of our method in preserving both ID classification accuracy and OOD detection performance on continuously shifting distributions., Comment: Accepted by ICCV 2023

This paper studies a distributed online convex optimization problem, where agents in an unbalanced network cooperatively minimize the sum of their time-varying local cost functions subject to a coupled inequality constraint. To solve this problem, we propose a distributed dual subgradient tracking algorithm, called DUST, which attempts to optimize a dual objective by means of tracking the primal constraint violations and integrating dual subgradient and push sum techniques. Different from most existing works, we allow the underlying network to be unbalanced with a column stochastic mixing matrix. We show that DUST achieves sublinear dynamic regret and constraint violations, provided that the accumulated variation of the optimal sequence grows sublinearly. If the standard Slater's condition is additionally imposed, DUST acquires a smaller constraint violation bound than the alternative existing methods applicable to unbalanced networks. Simulations on a plug-in electric vehicle charging problem demonstrate the superior convergence of DUST.