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
Proceedings ArticleDOI
Multi-relay strategy for imperfect channel information in sensor networks
N. Khajehnouri,Ali H. Sayed +1 more
TL;DR: A modified relay scheme is proposed to compensate for the influence of imperfect channel information on system performance and a multi-relay strategy for wireless networks is described.
Proceedings Article
An adaptive filter robust to data uncertainties
TL;DR: In this paper, a recursive procedure is derived that is based on solving local optimization problems that attemps to alleviate the worst-case effect of data uncertainties on filter performance, which turns out to have similarities with leakage-based adaptive filters.
Journal ArticleDOI
Displacement structure and maximum entropy
TL;DR: This correspondence presents a choice for the parameters that is motivated by a maximum-entropy formulation, and further motivates the introduction of the so-called generalized reflection coefficients which are, in general, different from the better known Schur coefficients.
Proceedings Article
Distributed Learning via Diffusion Adaptation with Application to Ensemble Learning
TL;DR: A distributed algorithm for online learning is proposed that is proved to guarantee a bounded excess risk and the bound can be made arbitrary small for sufficiently small step-sizes.
Proceedings ArticleDOI
Second-Order Guarantees in Federated Learning
TL;DR: In this article, the authors draw on recent results on the second-order optimality of stochastic gradient algorithms in centralized and decentralized settings, and establish secondorder guarantees for a class of federated learning algorithms.