Ali H. Sayed
YOU?
Author Swipe
View article: Improved High-probability Convergence Guarantees of Decentralized SGD
Improved High-probability Convergence Guarantees of Decentralized SGD Open
Convergence in high-probability (HP) has been receiving increasing interest, due to its attractive properties, such as exponentially decaying tail bounds and strong guarantees for each individual run of an algorithm. While HP guarantees ar…
View article: On the Escaping Efficiency of Distributed Adversarial Training Algorithms
On the Escaping Efficiency of Distributed Adversarial Training Algorithms Open
Adversarial training has been widely studied in recent years due to its role in improving model robustness against adversarial attacks. This paper focuses on comparing different distributed adversarial training algorithms--including centra…
View article: Policy Optimization in Multi-Agent Settings under Partially Observable Environments
Policy Optimization in Multi-Agent Settings under Partially Observable Environments Open
This work leverages adaptive social learning to estimate partially observable global states in multi-agent reinforcement learning (MARL) problems. Unlike existing methods, the proposed approach enables the concurrent operation of social le…
View article: Doubly Adaptive Social Learning
Doubly Adaptive Social Learning Open
In social learning, a network of agents assigns probability scores (beliefs) to some hypotheses of interest, which rule the generation of local streaming data observed by each agent. Belief formation takes place by means of an iterative tw…
View article: Social Learning: Opinion Formation and Decision-Making over Graphs
Social Learning: Opinion Formation and Decision-Making over Graphs Open
View article: Multi-agent Off-policy Actor-Critic Reinforcement Learning for Partially Observable Environments
Multi-agent Off-policy Actor-Critic Reinforcement Learning for Partially Observable Environments Open
View article: Minimizing the Probability of Error for Decision Making Over Graphs
Minimizing the Probability of Error for Decision Making Over Graphs Open
Distributed decision-making over graphs involves a group of agents that collaboratively work toward a common objective. In the social learning framework, the agents are tasked to infer an unknown state from a finite set by using a stream o…
View article: Differential Error Feedback for Communication-Efficient Decentralized Learning
Differential Error Feedback for Communication-Efficient Decentralized Learning Open
International audience
View article: Non-asymptotic performance of social machine learning under limited data
Non-asymptotic performance of social machine learning under limited data Open
View article: External validation and performance analysis of a deep learning-based model for the detection of intracranial hemorrhage
External validation and performance analysis of a deep learning-based model for the detection of intracranial hemorrhage Open
Purpose We aimed to investigate the external validation and performance of an FDA-approved deep learning model in labeling intracranial hemorrhage (ICH) cases on a real-world heterogeneous clinical dataset. Furthermore, we delved deeper in…
View article: Matching centralized learning performance via compressed decentralized learning with error feedback
Matching centralized learning performance via compressed decentralized learning with error feedback Open
International audience
View article: Differential Error Feedback for Communication-Efficient Decentralized Optimization
Differential Error Feedback for Communication-Efficient Decentralized Optimization Open
International audience
View article: Causal Impact Analysis for Asynchronous Decision Making
Causal Impact Analysis for Asynchronous Decision Making Open
Publisher Copyright: © 2024 IEEE.
View article: Multi-agent Off-policy Actor-Critic Reinforcement Learning for Partially Observable Environments
Multi-agent Off-policy Actor-Critic Reinforcement Learning for Partially Observable Environments Open
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. We assume that the n…
View article: Differential error feedback for communication-efficient decentralized learning
Differential error feedback for communication-efficient decentralized learning Open
Communication-constrained algorithms for decentralized learning and optimization rely on local updates coupled with the exchange of compressed signals. In this context, differential quantization is an effective technique to mitigate the ne…
View article: Accelerated Stochastic Min-Max Optimization Based on Bias-corrected Momentum
Accelerated Stochastic Min-Max Optimization Based on Bias-corrected Momentum Open
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 poin…
View article: Causal Influence in Federated Edge Inference
Causal Influence in Federated Edge Inference Open
In this paper, we consider a setting where heterogeneous agents with connectivity are performing inference using unlabeled streaming data. Observed data are only partially informative about the target variable of interest. In order to over…
View article: Graph Exploration for Effective Multiagent Q-Learning
Graph Exploration for Effective Multiagent Q-Learning Open
This article proposes an exploration technique for multiagent reinforcement learning (MARL) with graph-based communication among agents. We assume that the individual rewards received by the agents are independent of the actions by the oth…
View article: Detection of Malicious Agents in Social Learning
Detection of Malicious Agents in Social Learning Open
Non-Bayesian social learning is a framework for distributed hypothesis testing aimed at learning the true state of the environment. Traditionally, the agents are assumed to receive observations conditioned on the same true state, although …
View article: Asynchronous Diffusion Learning with Agent Subsampling and Local Updates
Asynchronous Diffusion Learning with Agent Subsampling and Local Updates Open
In this work, we examine a network of agents operating asynchronously, aiming to discover an ideal global model that suits individual local datasets. Our assumption is that each agent independently chooses when to participate throughout th…
View article: Diffusion Stochastic Optimization for Min-Max Problems
Diffusion Stochastic Optimization for Min-Max Problems Open
The optimistic gradient method is useful in addressing minimax optimization problems. Motivated by the observation that the conventional stochastic version suffers from the need for a large batch size on the order of $\mathcal{O}(\varepsil…
View article: Compressed Regression Over Adaptive Networks
Compressed Regression Over Adaptive Networks Open
View article: Causal Influence in Federated Edge Inference
Causal Influence in Federated Edge Inference Open
In this paper, we consider a setting where heterogeneous agents with connectivity are performing inference using unlabeled streaming data. Observed data are only partially informative about the target variable of interest. In order to over…
View article: Social Opinion Formation and Decision Making Under Communication Trends
Social Opinion Formation and Decision Making Under Communication Trends Open
This work studies the learning process over social networks under partial and random information sharing. In traditional social learning models, agents exchange full belief information with each other while trying to infer the true state o…
View article: Social Learning in Community Structured Graphs
Social Learning in Community Structured Graphs Open
Traditional social learning frameworks consider environments with a homogeneous state, where each agent receives observations conditioned on that true state of nature. In this work, we relax this assumption and study the distributed hypoth…
View article: Distributed Adaptive Learning Under Communication Constraints
Distributed Adaptive Learning Under Communication Constraints Open
We consider a network of agents that must solve an online optimization problem from continual observation of streaming data. To this end, the agents implement a distributed cooperative strategy where each agent is allowed to perform local …
View article: IEEE Systems, Man, and Cybernetics Society Information
IEEE Systems, Man, and Cybernetics Society Information Open
View article: On the Arithmetic and Geometric Fusion of Beliefs for Distributed Inference
On the Arithmetic and Geometric Fusion of Beliefs for Distributed Inference Open
We study the asymptotic learning rates of belief vectors in a distributed hypothesis testing problem under linear and log-linear combination rules. We show that under both combination strategies, agents are able to learn the truth exponent…
View article: Contributors
Contributors Open
View article: Masthead
Masthead Open