A
Ali H. Sayed
Researcher at École Polytechnique Fédérale de Lausanne
Publications - 766
Citations - 39568
Ali H. Sayed is an academic researcher from École Polytechnique Fédérale de Lausanne. The author has contributed to research in topics: Adaptive filter & Optimization problem. The author has an hindex of 81, co-authored 728 publications receiving 36030 citations. Previous affiliations of Ali H. Sayed include Harbin Engineering University & University of California, Los Angeles.
Papers
More filters
Posted Content
Dif-MAML: Decentralized Multi-Agent Meta-Learning.
TL;DR: The work provides a detailed theoretical analysis to show that the proposed cooperative fully-decentralized multi-agent meta-learning algorithm allows a collection of agents to attain agreement at a linear rate and to converge to a stationary point of the aggregate MAML objective even in non-convex environments.
Proceedings ArticleDOI
Decentralized consensus optimization with asynchrony and delays
TL;DR: An asynchronous, decentralized algorithm for consensus optimization that involves both primal and dual variables, uses fixed step-size parameters, and provably converges to the exact solution under a random agent assumption and both bounded and unbounded delay assumptions.
Posted Content
Asymptotic Performance of Adaptive Distributed Detection over Networks.
TL;DR: A fundamental scaling law is established for the probabilities of miss-detection and false-alarm, when the agents interact with each other according to distributed strategies that employ constant step-sizes.
Journal ArticleDOI
Multiagent Fully Decentralized Value Function Learning With Linear Convergence Rates
TL;DR: A fully decentralized multiagent algorithm for policy evaluation that achieves linear convergence with $O(1)$ memory requirements and combines off-policy learning, eligibility traces, and linear function approximation is developed.
Journal ArticleDOI
Diffusion LMS With Communication Delays: Stability and Performance Analysis
TL;DR: In this paper, the authors investigate the diffusion Least-mean-square (LMS) strategy where delayed intermediate estimates (due to the communication channels) are employed during the combination step.