Home

Person

Ali H. Sayed

This person has left EPFL

About
Privacy
Disclaimer

Graph Chatbot

Related publications (142)

Page 3 of 8

Partial Information Sharing Over Social Learning Networks

Ali H. Sayed, Virginia Bordignon

This work addresses the problem of sharing partial information within social learning strategies. In social learning, agents solve a distributed multiple hypothesis testing problem by performing two operations at each instant: first, agents incorporate inf ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023

Performance of Social Machine Learning under Limited Data

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

This paper studies the non-Asymptotic classification performance of the social machine learning strategy. This strategy involves an independent training phase followed by a cooperative inference phase to classify a growing number of samples. By considering ...

IEEE2023

Learning Graph Influence From Social Interactions

Ali H. Sayed, Virginia Bordignon, Augusto José Rabelo Almeida Santos

In social learning, agents form their opinions or beliefs about certain hypotheses by exchanging local information. This work considers the recent paradigm of weak graphs, where the network is partitioned into sending and receiving components, with the for ...

IEEE2020

Differential Error Feedback for Communication-Efficient Decentralized Optimization

Ali H. Sayed

Communication-constrained algorithms for decentralized learning and optimization rely on the exchange of quantized signals coupled with local updates. In this context, differential quantization is an effective technique to mitigate the negative impact of q ...

IEEE Computer Society2024

Explainability and Graph Learning From Social Interactions

Ali H. Sayed, Stefan Vlaski, Valentina Shumovskaia, Konstantinos Ntemos

Social learning algorithms provide models for the formation of opinions over social networks resulting from local reasoning and peer-to-peer exchanges. Interactions occur over an underlying graph topology, which describes the flow of information among the ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

Decentralized Gan Training Through Diffusion Learning

Ali H. Sayed, Noé Stauffer

Most available studies on distributed GAN architectures focus on implementations with a fusion center. In this work, we propose a fully decentralized scheme by employing a diffusion strategy to train a network of GANs. We interpret the training procedure a ...

IEEE2022

Logical Team Q-learning: An approach towards factored policies in cooperative MARL

Ali H. Sayed, Lucas Cesar Eduardo Cassano

We address the challenge of learning factored policies in cooperative MARL scenarios. In particular, we consider the situation in which a team of agents collaborates to optimize a common cost. The goal is to obtain factored policies that determine the indi ...

MICROTOME PUBLISHING2021

Cover: A Cluster-Based Variance Reduced Method For Online Learning

Ali H. Sayed, Kun Yuan, Bicheng Ying

In this paper, we develop a stochastic-gradient learning algorithm for situations involving streaming data that arise from an underlying clustered structure. In such settings, the variance of gradient noise can be decomposed into the in-cluster variance si ...

IEEE2019

Learning Over Multitask Graphs-Part I: Stability Analysis

Ali H. Sayed, Stefan Vlaski, Roula Nassif

This paper formulates a multitask optimization problem where agents in the network have individual objectives to meet, or individual parameter vectors to estimate, subject to a smoothness condition over the graph. The smoothness condition softens the trans ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020

Efficient Variance-Reduced Learning Over Multi-Agent Networks

Ali H. Sayed, Kun Yuan, Bicheng Ying

This work develops a fully decentralized variance-reduced learning algorithm for multi-agent networks where nodes store and process the data locally and are only allowed to communicate with their immediate neighbors. In the proposed algorithm, there is no ...

IEEE COMPUTER SOC2018

Adaptive Diffusion With Compressed Communication

Ali H. Sayed

We consider multi-agent networks that aim at solving, cooperatively and online, distributed optimization problems under communication constraints. We propose the ACTC (Adapt-Compress-Then-Combine) diffusion strategy, which leverages differential randomized ...

IEEE2022

Learning Bollobas-Riordan Graphs Under Partial Observability

Ali H. Sayed

This work examines the problem of learning the topology of a network (graph learning) from the signals produced at a subset of the network nodes (partial observability). This challenging problem was recently tackled assuming that the topology is drawn acco ...

IEEE2021

A Fundamental Limit of Distributed Hypothesis Testing Under Memoryless Quantization

Ali H. Sayed, Emre Telatar, Mert Kayaalp, Yunus Inan

We consider a distributed binary hypothesis testing setup where multiple nodes send quantized information to a central processor, which is oblivious to the nodes' statistics. We study the regime where the missed detection (type-II error) probability decays ...

IEEE2022

Second-order guarantees in centralized, federated and decentralized nonconvex optimization

Ali H. Sayed, Stefan Vlaski

Rapid advances in data collection and processing capabilities have allowed for the use of increasingly complex models that give rise to nonconvex optimization problems. These formulations, however, can be arbitrarily difficult to solve in general, in the s ...

INT PRESS BOSTON, INC2020

Decentralized Decision-Making Over Multi-Task Networks

Ali H. Sayed

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. In this work we propose ...

ELSEVIER SCIENCE BV2019

Graph Exploration for Effective Multiagent Q-Learning

Ali H. Sayed, Ainur Zhaikhan

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 other agents, while ...

Ieee-Inst Electrical Electronics Engineers Inc2024

Detection of Malicious Agents in Social Learning

Ali H. Sayed, Mert Kayaalp, Valentina Shumovskaia

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 it is also possib ...

IEEE Institute of Electrical and Electronics Engineers2024

Decision-making algorithms for learning and adaptation with application to COVID-19 data

Ali H. Sayed

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. A key observat ...

ELSEVIER2022

Social Learning under Randomized Collaborations

Ali H. Sayed

We study a social learning scheme where at every time instant, each agent chooses to receive information from one of its neighbors at random. We show that under this sparser communication scheme, the agents learn the truth eventually and the asymptotic con ...

IEEE2023

Adaptation and Learning Over Networks Under Subspace Constraints & x2014;Part II: Performance Analysis

Ali H. Sayed, Stefan Vlaski, Roula Nassif

Part & x00A0;I of this paper considered optimization problems over networks where agents have individual objectives to meet, or individual parameter vectors to estimate, subject to subspace constraints that require the objectives across the network to lie ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020