scispace - formally typeset
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

Linear Speedup in Saddle-Point Escape for Decentralized Non-Convex Optimization

TL;DR: The results imply that a linear speedup can be expected in the pursuit of second-order stationary points, which exclude local maxima as well as strict saddle-points and correspond to local or even global minima in many important learning settings.
Proceedings ArticleDOI

Social Learning with Disparate Hypotheses

TL;DR: This paper proposes a scheme with adaptive combination weights and provides sufficient conditions that enable all agents to correctly identify their true hypotheses and analyzes the asymptotic behavior of agents' beliefs under the proposed social learning algorithm.
Journal ArticleDOI

Message from the Editor-in-Chief

TL;DR: While clearly diverse in topic and scope, all three manuscripts in this issue of EID provide excellent examples of how human factors principles should be embedded in every step of a product design.
Proceedings Article

A dynamic antenna scheduling strategy for multi-user MIMO communications

TL;DR: By characterizing the probability distribution of the so-called signal-to-leakage-plus-noise (SLNR) ratio, it is shown that there is an optimal set of receive antennas that maximizes the system performance for each channel realization.
Proceedings ArticleDOI

Fundamental inertia conditions for the solution of H/sup /spl infin//-problems

TL;DR: In this article, the relation between the solutions of two minimization problems with indefinite quadratic forms is established by invoking a fundamental set of inertia conditions, which are automatically satisfied in a standard Hilbert space setting, but nevertheless turn out to mark the differences between the two optimization problems in indefinite metric spaces.