Picture for Yuval Peres

Yuval Peres

Multiplayer Bandit Learning, from Competition to Cooperation

Add code
Aug 03, 2019
Figure 1 for Multiplayer Bandit Learning, from Competition to Cooperation
Figure 2 for Multiplayer Bandit Learning, from Competition to Cooperation
Figure 3 for Multiplayer Bandit Learning, from Competition to Cooperation
Viaarxiv icon

Sorted Top-k in Rounds

Add code
Jun 12, 2019
Figure 1 for Sorted Top-k in Rounds
Figure 2 for Sorted Top-k in Rounds
Figure 3 for Sorted Top-k in Rounds
Figure 4 for Sorted Top-k in Rounds
Viaarxiv icon

Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without

Add code
May 01, 2019
Viaarxiv icon

Online Learning with an Almost Perfect Expert

Add code
Sep 27, 2018
Figure 1 for Online Learning with an Almost Perfect Expert
Figure 2 for Online Learning with an Almost Perfect Expert
Figure 3 for Online Learning with an Almost Perfect Expert
Viaarxiv icon

Mixing time estimation in reversible Markov chains from a single sample path

Add code
Aug 24, 2017
Viaarxiv icon

Tight Lower Bounds for Multiplicative Weights Algorithmic Families

Add code
Jul 14, 2016
Figure 1 for Tight Lower Bounds for Multiplicative Weights Algorithmic Families
Viaarxiv icon

Towards Optimal Algorithms for Prediction with Expert Advice

Add code
Jul 11, 2016
Viaarxiv icon

Approval Voting and Incentives in Crowdsourcing

Add code
Sep 07, 2015
Figure 1 for Approval Voting and Incentives in Crowdsourcing
Figure 2 for Approval Voting and Incentives in Crowdsourcing
Figure 3 for Approval Voting and Incentives in Crowdsourcing
Viaarxiv icon

Bandit Convex Optimization: sqrt{T} Regret in One Dimension

Add code
Feb 23, 2015
Figure 1 for Bandit Convex Optimization: sqrt{T} Regret in One Dimension
Figure 2 for Bandit Convex Optimization: sqrt{T} Regret in One Dimension
Viaarxiv icon

Online Learning with Composite Loss Functions

Add code
May 18, 2014
Viaarxiv icon