← Back to directory

Yishay Mansour

Researcher Next ID · RN-042152

Researcher · Computer Science

Google (United States)

Mountain View, Israel

Accepting doctoral researchersFunding unknown
Works count
492
Citation count
21,555
H-index
67
i10-index
225

Research interests

Computer Science
Decision Sciences
Advanced Bandit Algorithms Research
Machine Learning and Algorithms
Auction Theory and Applications
Optimization and Search Problems
Game Theory and Applications

Publications

  • Three Approaches for Personalization with Applications to Federated Learning

    arXiv (Cornell University) · 2020 · 10.48550/arxiv.2002.10619

  • Implementing the “Wisdom of the Crowd”

    Journal of Political Economy · 2014 · 10.1086/676597

  • Learning Bounds for Importance Weighting

    · 2010

  • Domain Adaptation: Learning Bounds and Algorithms

    arXiv (Cornell University) · 2009 · https://doi.org/10.48550/arxiv.0902.3430

  • Agnostically Learning Halfspaces

    SIAM Journal on Computing · 2008 · 10.1137/060649057

  • Domain Adaptation with Multiple Sources

    Journal · 2008

  • The Shrinking Generator

    Lecture notes in computer science · 2007 · 10.1007/3-540-48329-2_3

  • Learning, Regret Minimization, and Equilibria

    Algorithmic Game Theory · 2007 · 10.1017/cbo9780511800481.006

  • Action Elimination and Stopping Conditions for the Multi-Armed Bandit and Reinforcement Learning Problems

    Journal of Machine Learning Research · 2006

  • Buffer Overflow Management in QoS Switches

    SIAM Journal on Computing · 2004 · 10.1137/s0097539701399666

  • Convergence Time to Nash Equilibria

    Lecture notes in computer science · 2003 · 10.1007/3-540-45061-0_41

  • A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov Decision Processes

    Machine Learning · 2002 · 10.1023/a:1017932429737

  • PAC Bounds for Multi-armed Bandit and Markov Decision Processes

    Lecture notes in computer science · 2002 · 10.1007/3-540-45435-7_18

  • Learning Rates for Q-Learning

    Lecture notes in computer science · 2001 · 10.1007/3-540-44581-1_39

  • Nash convergence of gradient dynamics in general-sum games

    · 2000

  • Policy Gradient Methods for Reinforcement Learning with Function Approximation

    Journal · 1999

  • An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clustering

    · 1998 · 10.1007/978-94-011-5014-9_18

  • An $\Omega(D\log (N/D))$ Lower Bound for Broadcast in Radio Networks

    SIAM Journal on Computing · 1998 · 10.1137/s0097539794279109

  • A construction of a cipher from a single pseudorandom permutation

    Journal of Cryptology · 1997 · 10.1007/s001459900025

  • An experimental and theoretical comparison of model selection methods

    · 1995 · 10.1145/225298.225301

  • On the learnability of discrete distributions

    · 1994 · 10.1145/195058.195155

  • Weakly learning DNF and characterizing statistical query learning using Fourier analysis

    · 1994 · 10.1145/195058.195147

  • Constant depth circuits, Fourier transform, and learnability

    Journal of the ACM · 1993 · https://doi.org/10.1145/174130.174138

  • Learning Decision Trees Using the Fourier Spectrum

    SIAM Journal on Computing · 1993 · 10.1137/0222080

Current projects

    No projects listed.