Publications by Ali H. Sayed | EPFL Graph Search

Diffusion Stochastic Optimization for Min-Max Problems

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 O(ϵ-2) to achieve an ϵ-stationary solut ...

2025

On the Trade-off between Flatness and Optimization in Distributed Learning

Ali H. Sayed

Institute of Electrical and Electronics Engineers (IEEE)2025

Decentralized Adversarial Training over Graphs

Ali H. Sayed, Elsa Rizk

Institute of Electrical and Electronics Engineers (IEEE)2025

Multi-Agent Reinforcement Learning in Partially Observable Environments Using Social Learning

Ali H. Sayed, Ainur Zhaikhan

This work employs a social learning strategy to estimate the global state in a partially observable multi-agent reinforcement learning (MARL) setting. We prove that the proposed methodology can achieve results within an ε-neighborhood of the solution for a ...

IEEE2025

Social Learning with Dependent Agents

Ali H. Sayed

Social learning strategies implement a distributed decision-making process where several agents, connected over a graph, exchange their beliefs about some hypotheses of interest. Each agent uses some local model that describes the marginal distribution of ...

IEEE2025

Optimal Combination Policies for Error Exponent Maximization in Social Learning

Ali H. Sayed, Mert Kayaalp, Ping Hu

Distributed decision-making over networks involves multiple agents collaborating to achieve a common goal. In the social learning process, where agents aim at inferring an unknown state from a stream of local observations, the probability of error in their ...

IEEE2025

Masked Diffusion Strategy for Privacy-Preserving Distributed Learning

Ali H. Sayed

To protect both local gradients and estimated parameters in distributed learning, this paper introduces a masked diffusion (MD) strategy, leading to two algorithms: the MD stochastic gradient (MD-SG) and the MD primal-dual stochastic gradient (MPD-SG). The ...

2025

Fundamental Social Learning Scaling Law for Tracking Hidden Markov Models

Ali H. Sayed, Malek Khammassi

This paper studies the problem of interconnected agents collaborating to track a dynamic state from partially informative observations, where the dynamic state evolves according to a slowly varying finite-state Markov chain. Although the centralized versio ...

IEEE2025

Diffusion Learning Over Adaptive Competing Networks

Ali H. Sayed

In this paper, we study a dynamic game between two networks. The networks compete by optimizing two coupled objective functions. Agents within the same network work toward a common goal and are regarded as cooperative agents; they exchange their strategies ...

IEEE2025

Non-asymptotic performance of social machine learning under limited data

Ali H. Sayed, Virginia Bordignon, Mert Kayaalp, Ping Hu

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. This framework addresses the problem of classifyin ...

2025