1 code implementation • NeurIPS 2019 • Andrey Kolobov, Yuval Peres, Cheng Lu, Eric J. Horvitz
From traditional Web search engines to virtual assistants and Web accelerators, services that rely on online information need to continually keep track of remote content changes by explicitly requesting content updates from remote sources (e. g., web pages).
no code implementations • 3 Aug 2019 • Simina Brânzei, Yuval Peres
We show that competing players explore less than a single player: there is $p^* \in (m, g)$ so that for all $p > p^*$, the players stay at the predictable arm.
no code implementations • 12 Jun 2019 • Mark Braverman, Jieming Mao, Yuval Peres
When the comparisons are noiseless, we characterize how the optimal sample complexity depends on the number of rounds (up to a polylogarithmic factor for general $r$ and up to a constant factor for $r=1$ or 2).
no code implementations • 28 Apr 2019 • Sébastien Bubeck, Yuanzhi Li, Yuval Peres, Mark Sellke
We consider the non-stochastic version of the (cooperative) multi-player multi-armed bandit problem.
no code implementations • 30 Jul 2018 • Simina Brânzei, Yuval Peres
We study the multiclass online learning problem where a forecaster makes a sequence of predictions using the advice of $n$ experts.
no code implementations • NeurIPS 2015 • Daniel Hsu, Aryeh Kontorovich, David A. Levin, Yuval Peres, Csaba Szepesvári
The interval is constructed around the relaxation time $t_{\text{relax}} = 1/\gamma$, which is strongly related to the mixing time, and the width of the interval converges to zero roughly at a $1/\sqrt{n}$ rate, where $n$ is the length of the sample path.
no code implementations • 11 Jul 2016 • Nick Gravin, Yuval Peres, Balasubramanian Sivan
We study the fundamental problem of prediction with expert advice and develop regret lower bounds for a large family of algorithms for this problem.
no code implementations • 23 Feb 2015 • Sébastien Bubeck, Ofer Dekel, Tomer Koren, Yuval Peres
We analyze the minimax regret of the adversarial bandit convex optimization problem.
no code implementations • 19 Feb 2015 • Nihar B. Shah, Dengyong Zhou, Yuval Peres
The growing need for labeled training data has made crowdsourcing an important part of machine learning.
no code implementations • 10 Sep 2014 • Nick Gravin, Yuval Peres, Balasubramanian Sivan
Further, we show that the optimal algorithm for $2$ and $3$ experts is a probability matching algorithm (analogous to Thompson sampling) against a particular randomized adversary.
no code implementations • 18 May 2014 • Ofer Dekel, Jian Ding, Tomer Koren, Yuval Peres
This class includes problems where the algorithm's loss is the minimum over the recent adversarial values, the maximum over the recent values, or a linear combination of the recent values.
no code implementations • 11 Oct 2013 • Ofer Dekel, Jian Ding, Tomer Koren, Yuval Peres
We prove that the player's $T$-round minimax regret in this setting is $\widetilde{\Theta}(T^{2/3})$, thereby closing a fundamental gap in our understanding of learning with bandit feedback.