Y
Yishay Mansour
Researcher at Tel Aviv University
Publications - 546
Citations - 30407
Yishay Mansour is an academic researcher from Tel Aviv University. The author has contributed to research in topics: Regret & Upper and lower bounds. The author has an hindex of 80, co-authored 511 publications receiving 26984 citations. Previous affiliations of Yishay Mansour include Technion – Israel Institute of Technology & IBM.
Papers
More filters
Posted Content
On Propagating Updates in a Byzantine Environment
TL;DR: This work proposes two epidemic-style diffusion algorithms and two measures that characterize the efficiency of diffusion algorithms in general, and characterize both of their algorithms according to these measures, and proves lower bounds with regards toThese measures that show that the authors' algorithms are close to optimal.
Proceedings Article
Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexity
TL;DR: In this article, a differentially private learner for halfspaces over a finite grid was presented, with sample complexity approximating d^{2.5}\cdot 2^{\log^*|G|}, which is the state-of-the-art.
Proceedings ArticleDOI
Dynamics of Evolving Social Groups
TL;DR: This paper introduces an analytic framework for studying the dynamics of exclusive social groups, which considers several natural admission rules including majority and consensus, and studies both growing groups and fixed-size groups.
Posted Content
Probe Scheduling for Efficient Detection of Silent Failures
Edith Cohen,Edith Cohen,Avinatan Hassidim,Avinatan Hassidim,Haim Kaplan,Yishay Mansour,Danny Raz,Danny Raz,Yoav Tzur +8 more
TL;DR: In this paper, the authors formulate a general model which unifies the treatment of probe scheduling mechanisms, stochastic or deterministic, and different cost objectives - minimizing average detection time (SUM) or worst-case detection times (MAX).
On Learning Conjunctions with Malicious Noise.
Yishay Mansour,Michal Parnas +1 more
TL;DR: It is shown how to learn monomials in the presence of malicious noise, when the underlined distribution is a product distribution, and the results apply not only to product distributions but to a wide class of distributions.