9 citations · 17 across the 3 of their papers we have counts for
3 papers
MaxGap Bandit: Adaptive Algorithms for Approximate Ranking
Sumeet Katariya, Ardhendu Tripathy, Robert Nowak
This paper studies the problem of adaptively sampling from K distributions (arms) in order to identify the largest gap between any two adjacent means. We call this the MaxGap-bandi…
Stochastic Rank-1 Bandits
Sumeet Katariya, Branislav Kveton, Csaba Szepesvari +2
We propose stochastic rank- bandits, a class of online learning problems where at each step a learning agent chooses a pair of row and column arms, and receives the product of t…
Sparse Dueling Bandits
Kevin Jamieson, Sumeet Katariya, Atul Deshpande +1
The dueling bandit problem is a variation of the classical multi-armed bandit in which the allowable actions are noisy comparisons between pairs of arms. This paper focuses on a ne…