Search Results for author:
Found 84 papers, 6 papers with code
Multi-agent Off-policy Actor-Critic Reinforcement Learning for Partially Observable Environments
This study proposes the use of a social learning method to estimate a global state within a multi-agent off-policy actor-critic algorithm for reinforcement learning (RL) operating in a partially observable environment.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
On the Trade-off between Flatness and Optimization in Distributed Learning
This paper proposes a theoretical framework to evaluate and compare the performance of gradient-descent algorithms for distributed learning in relation to their behavior around local minima in nonconvex environments.
Differential error feedback for communication-efficient decentralized learning
The results establish that, in the small step-size regime and with a finite number of bits, it is possible to attain the performance achievable in the absence of compression.
Accelerated Stochastic Min-Max Optimization Based on Bias-corrected Momentum
Lower-bound analyses for nonconvex strongly-concave minimax optimization problems have shown that stochastic first-order algorithms require at least $\mathcal{O}(\varepsilon^{-4})$ oracle complexity to find an $\varepsilon$-stationary point.
Causal Influence in Federated Edge Inference
To evaluate how each agent influences the overall decision, we adopt a causal framework in order to distinguish the actual influence of agents from mere correlations within the decision-making process.
Asynchronous Diffusion Learning with Agent Subsampling and Local Updates
In this work, we examine a network of agents operating asynchronously, aiming to discover an ideal global model that suits individual local datasets.
Diffusion Stochastic Optimization for Min-Max Problems
The optimistic gradient method is useful in addressing minimax optimization problems.
Causal Influences over Social Learning Networks
This paper investigates causal influences between agents linked by a social graph and interacting over time.
Non-Asymptotic Performance of Social Machine Learning Under Limited Data
This paper studies the probability of error associated with the social machine learning framework, which involves an independent training phase followed by a cooperative decision-making phase over a graph.
Graph Exploration for Effective Multi-agent Q-Learning
Moreover, the proposed scheme allows agents to communicate in a fully decentralized manner with minimal information exchange.
Compressed Regression over Adaptive Networks
In this work we derive the performance achievable by a network of distributed agents that solve, adaptively and in the presence of communication constraints, a regression problem.
Decentralized Adversarial Training over Graphs
The vulnerability of machine learning models to adversarial attacks has been attracting considerable attention in recent years.
On the Fusion Strategies for Federated Decision Making
We consider the problem of information aggregation in federated decision making, where a group of agents collaborate to infer the underlying state of nature without sharing their private data with the central processor or each other.
Multi-Agent Adversarial Training Using Diffusion Learning
This work focuses on adversarial learning over graphs.
Policy Evaluation in Decentralized POMDPs with Belief Sharing
As a remedy, we propose a fully decentralized belief forming strategy that relies on individual updates and on localized interactions over a communication network.
Memory-Aware Social Learning under Partial Information Sharing
We devise a novel learning strategy where each agent forms a valid belief by completing the partial beliefs received from its neighbors.
Enforcing Privacy in Distributed Learning with Performance Guarantees
We study the privatization of distributed learning and optimization strategies.
Distributed Bayesian Learning of Dynamic States
This work studies networked agents cooperating to track a dynamical state of nature under partial information.
Local Graph-homomorphic Processing for Privatized Distributed Systems
We study the generation of dependent random numbers in a distributed fashion in order to enable privatized distributed learning by networked agents.
Networked Signal and Information Processing
Moreover, and significantly, theory and applications show that networked agents, through cooperation and sharing, are able to match the performance of cloud or federated solutions, while offering the potential for improved privacy, increasing resilience, and saving resources.
Quantization for decentralized learning under subspace constraints
In this paper, we consider decentralized optimization problems where agents have individual cost functions to minimize subject to subspace constraints that require the minimizers across the network to lie in low-dimensional subspaces.
On the Arithmetic and Geometric Fusion of Beliefs for Distributed Inference
We study the asymptotic learning rates under linear and log-linear combination rules of belief vectors in a distributed hypothesis testing problem.
Dencentralized learning in the presence of low-rank noise
Observations collected by agents in a network may be unreliable due to observation noise or interference.
Optimal Aggregation Strategies for Social Learning over Graphs
Adaptive social learning is a useful tool for studying distributed decision-making problems over graphs.
Privatized Graph Federated Learning
Federated learning is a semi-distributed algorithm, where a server communicates with multiple dispersed clients to learn a global model.
Explainability and Graph Learning from Social Interactions
Social learning algorithms provide models for the formation of opinions over social networks resulting from local reasoning and peer-to-peer exchanges.
Online Graph Learning from Social Interactions
For a given graph topology, these algorithms allow for the prediction of formed opinions.
Social Opinion Formation and Decision Making Under Communication Trends
We show that agents can learn the true hypothesis even if they do not discuss it, at rates comparable to traditional social learning.
Combinations of Adaptive Filters
Adaptive filters are at the core of many signal processing applications, ranging from acoustic noise supression to echo cancelation, array beamforming, channel equalization, to more recent sensor network applications in surveillance, target localization, and tracking.
Learning from Heterogeneous Data Based on Social Interactions over Graphs
In the proposed social machine learning (SML) strategy, two phases are present: in the training phase, classifiers are independently trained to generate a belief over a set of hypotheses using a finite number of training samples; in the prediction phase, classifiers evaluate streaming unlabeled observations and share their instantaneous beliefs with neighboring classifiers.
Distributed Adaptive Learning Under Communication Constraints
We propose a diffusion strategy nicknamed as ACTC (Adapt-Compress-Then-Combine), which relies on the following steps: i) an adaptation step where each agent performs an individual stochastic-gradient update with constant step-size; ii) a compression step that leverages a recently introduced class of stochastic compression operators; and iii) a combination step where each agent combines the compressed updates received from its neighbors.
Hidden Markov Modeling over Graphs
This work proposes a multi-agent filtering algorithm over graphs for finite-state hidden Markov models (HMMs), which can be used for sequential state estimation or for tracking opinion formation over dynamic social networks.
A Graph Federated Architecture with Privacy Preserving Learning
Thus in this work, we develop a private multi-server federated learning scheme, which we call graph federated learning.
Competing Adaptive Networks
Adaptive networks have the capability to pursue solutions of global stochastic optimization problems by relying only on local interactions within neighborhoods.
Deception in Social Learning
Then, we will explain that it is possible for such attacks to succeed by showing that strategies exist that can be adopted by the malicious agents for this purpose.
Decision-Making Algorithms for Learning and Adaptation with Application to COVID-19 Data
This work focuses on the development of a new family of decision-making algorithms for adaptation and learning, which are specifically tailored to decision problems and are constructed by building up on first principles from decision theory.
Federated Learning under Importance Sampling
Federated learning encapsulates distributed learning strategies that are managed by a central unit.
Second-Order Guarantees in Federated Learning
Federated learning is a useful framework for centralized learning from distributed data under practical considerations of heterogeneity, asynchrony, and privacy.
Optimal Importance Sampling for Federated Learning
Federated learning involves a mixture of centralized and decentralized processing tasks, where a server regularly selects a sample of the agents and these in turn sample their local data to compute stochastic gradients for their learning updates.
Social learning under inferential attacks
A common assumption in the social learning literature is that agents exchange information in an unselfish manner.
Network Classifiers Based on Social Learning
Combination over time means that the classifiers respond to streaming data during testing and continue to improve their performance even during this phase.
Graph-Homomorphic Perturbations for Private Decentralized Learning
Decentralized algorithms for stochastic optimization and learning rely on the diffusion of information as a result of repeated local exchanges of intermediate estimates.
Dif-MAML: Decentralized Multi-Agent Meta-Learning
The formalism of meta-learning is actually well-suited to this decentralized setting, where the learner would be able to benefit from information and computational power spread across the agents.
Partial Information Sharing over Social Learning Networks
Instead of sharing the entirety of their beliefs, this work considers the case in which agents will only share their beliefs regarding one hypothesis of interest, with the purpose of evaluating its validity, and draws conditions under which this policy does not affect truth learning.
A Multi-Agent Primal-Dual Strategy for Composite Optimization over Distributed Features
This work studies multi-agent sharing optimization problems with the objective function being the sum of smooth local functions plus a convex (possibly non-smooth) function coupling all agents.
Logical Team Q-learning: An approach towards factored policies in cooperative MARL
We derive LTQL as a stochastic approximation to a dynamic programming method we introduce in this work.
Tracking Performance of Online Stochastic Learners
The utilization of online stochastic algorithms is popular in large-scale learning settings due to their ability to compute updates on the fly, without the need to store and process data in large batches.
Second-Order Guarantees in Centralized, Federated and Decentralized Nonconvex Optimization
Rapid advances in data collection and processing capabilities have allowed for the use of increasingly complex models that give rise to nonconvex optimization problems.
Dynamic Federated Learning
Federated learning has emerged as an umbrella term for centralized coordination strategies in multi-agent environments.
Multitask learning over graphs: An Approach for Distributed, Streaming Machine Learning
Multitask learning is an approach to inductive transfer learning (using what is learned for one problem to assist in another problem) and helps improve generalization performance relative to learning each task separately by using the domain information contained in the training signals of related tasks as an inductive bias.
Graph Learning Under Partial Observability
Many optimization, inference and learning tasks can be accomplished efficiently by means of decentralized processing algorithms where the network topology (i. e., the graph) plays a critical role in enabling the interactions among neighboring nodes.
Social Learning with Partial Information Sharing
This work studies the learning abilities of agents sharing partial beliefs over social networks.
Signal Processing Multiagent Systems
Linear Speedup in Saddle-Point Escape for Decentralized Non-Convex Optimization
Under appropriate cooperation protocols and parameter choices, fully decentralized solutions for stochastic optimization have been shown to match the performance of centralized solutions and result in linear speedup (in the number of agents) relative to non-cooperative approaches in the strongly-convex setting.
Network Classifiers With Output Smoothing
This work introduces two strategies for training network classifiers with heterogeneous agents.
Regularized Diffusion Adaptation via Conjugate Smoothing
The purpose of this work is to develop and study a distributed strategy for Pareto optimization of an aggregate cost consisting of regularized risks.
ISL: A novel approach for deep exploration
In this article we explore an alternative approach to address deep exploration and we introduce the ISL algorithm, which is efficient at performing deep exploration.
Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization
Recent years have seen increased interest in performance guarantees of gradient descent algorithms for non-convex optimization.
Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points
In Part I [2] of this work we established that agents cluster around a network centroid and proceeded to study the dynamics of this point.
Graph Learning over Partially Observed Diffusion Networks: Role of Degree Concentration
This claim is proved for three matrix estimators: i) the Granger estimator that adapts to the partial observability setting the solution that is exact under full observability ; ii) the one-lag correlation matrix; and iii) the residual estimator based on the difference between two consecutive time samples.
On the Influence of Bias-Correction on Distributed Stochastic Optimization
It is still unknown {\em whether}, {\em when} and {\em why} these bias-correction methods can outperform their traditional counterparts (such as consensus and diffusion) with noisy gradient and constant step-sizes.
Decentralized Decision-Making Over Multi-Task Networks
In important applications involving multi-task networks with multiple objectives, agents in the network need to decide between these multiple objectives and reach an agreement about which single objective to follow for the network.
Multi-Agent Fully Decentralized Value Function Learning with Linear Convergence Rates
In this scenario, agents collaborate to estimate the value function of a target team policy.
Learning Kolmogorov Models for Binary Random Variables
We summarize our recent findings, where we proposed a framework for learning a Kolmogorov model, for a collection of binary random variables.
BIG-bench Machine Learning
Interpretable Machine Learning
+1
Supervised Learning Under Distributed Features
This work studies the problem of learning under both large datasets and large-dimensional feature space scenarios.
Stochastic Learning under Random Reshuffling with Constant Step-sizes
In empirical risk optimization, it has been observed that stochastic gradient implementations that rely on random reshuffling of the data achieve better performance than implementations that rely on sampling the data uniformly.
Distributed Coupled Multi-Agent Stochastic Optimization
In this formulation, each agent is influenced by only a subset of the entries of a global parameter vector or model, and is subject to convex constraints that are only known locally.
Optimization and Control
Variance-Reduced Stochastic Learning under Random Reshuffling
First, it resolves this open issue and provides the first theoretical guarantee of linear convergence under random reshuffling for SAGA; the argument is also adaptable to other variance-reduced algorithms.
Variance-Reduced Stochastic Learning by Networked Agents under Random Reshuffling
For such situations, the balanced gradient computation property of AVRG becomes a real advantage in reducing idle time caused by unbalanced local data storage requirements, which is characteristic of other reduced-variance gradient algorithms.
Performance Limits of Stochastic Sub-Gradient Learning, Part II: Multi-Agent Case
The analysis in Part I revealed interesting properties for subgradient learning algorithms in the context of stochastic optimization when gradient noise is present.
Multitask diffusion adaptation over networks with common latent representations
Online learning with streaming data in a distributed and collaborative manner can be useful in a wide range of applications.
Decentralized Clustering and Linking by Networked Agents
We consider the problem of decentralized clustering and estimation over multi-task networks, where agents infer and track different models of interest.
On the Influence of Momentum Acceleration on Online Learning
The article examines in some detail the convergence rate and mean-square-error performance of momentum stochastic gradient methods in the constant step-size and slow adaptation regime.
Online Dual Coordinate Ascent Learning
The stochastic dual coordinate-ascent (S-DCA) technique is a useful alternative to the traditional stochastic gradient-descent algorithm for solving large-scale optimization problems due to its scalability to large data sets and strong theoretical guarantees.
Asynchronous adaptive networks
In a recent article [1] we surveyed advances related to adaptation, learning, and optimization over synchronous networks.
Performance Limits of Stochastic Sub-Gradient Learning, Part I: Single Agent Case
In this work and the supporting Part II, we examine the performance of stochastic sub-gradient learning strategies under weaker conditions than usually considered in the literature.
Information Exchange and Learning Dynamics over Weakly-Connected Adaptive Networks
The paper examines the learning mechanism of adaptive agents over weakly-connected graphs and reveals an interesting behavior on how information flows through such topologies.
Distributed Clustering and Learning Over Networks
In doing so, the resulting algorithm enables the agents to identify their clusters and to attain improved learning and estimation accuracy over networks.
Stability and Performance Limits of Adaptive Primal-Dual Networks
It is shown that this method allows the AL algorithm to approach the performance of consensus and diffusion strategies but that it remains less stable than these other strategies.
Dictionary Learning over Distributed Models
In this paper, we consider learning dictionary models over a network of agents, where each agent is only in charge of a portion of the dictionary elements.
Distributed Policy Evaluation Under Multiple Behavior Strategies
We apply diffusion strategies to develop a fully-distributed cooperative reinforcement learning algorithm in which agents in a network communicate only with their immediate neighbors to improve predictions about their environment.
Asynchronous Adaptation and Learning over Networks --- Part I: Modeling and Stability Analysis
In this work and the supporting Parts II [2] and III [3], we provide a rather detailed analysis of the stability and performance of asynchronous strategies for solving distributed optimization and adaptation problems over networks.
Asynchronous Adaptation and Learning over Networks - Part III: Comparison Analysis
First, the results establish that the performance of adaptive networks is largely immune to the effect of asynchronous events: the mean and mean-square convergence rates and the asymptotic bias values are not degraded relative to synchronous or centralized implementations.
Asynchronous Adaptation and Learning over Networks - Part II: Performance Analysis
The expressions reveal how the various parameters of the asynchronous behavior influence network performance.
Diffusion Adaptation over Networks
The agents are linked together through a connection topology, and they cooperate with each other through local interactions to solve distributed optimization, estimation, and inference problems in real-time.
