138 citations · 1.5k across the 136 of their papers we have counts for
6 papers · 2 filters
Risk-Constrained Thompson Sampling for CVaR Bandits
Joel Q. L. Chang, Qiuyu Zhu, Vincent Y. F. Tan
The multi-armed bandit (MAB) problem is a ubiquitous decision-making problem that exemplifies the exploration-exploitation tradeoff. Standard formulations exclude risk in decision…
Probabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with Corruptions
Zixin Zhong, Wang Chi Cheung, Vincent Y. F. Tan
We consider a best arm identification (BAI) problem for stochastic bandits with adversarial corruptions in the fixed-budget setting of T steps. We design a novel randomized algorit…
MC2G: An Efficient Algorithm for Matrix Completion with Social and Item Similarity Graphs
Qiaosheng Zhang, Geewon Suh, Changho Suh +1
In this paper, we design and analyze MC2G (Matrix Completion with 2 Graphs), an algorithm that performs matrix completion in the presence of social and item similarity graphs. MC2G…
Thompson Sampling Algorithms for Mean-Variance Bandits
Qiuyu Zhu, Vincent Y. F. Tan
The multi-armed bandit (MAB) problem is a classical learning task that exemplifies the exploration-exploitation tradeoff. However, standard formulations do not take into account {\…
Tight Regret Bounds for Noisy Optimization of a Brownian Motion
Zexin Wang, Vincent Y. F. Tan, Jonathan Scarlett
We consider the problem of Bayesian optimization of a one-dimensional Brownian motion in which the adaptively chosen observations are corrupted by Gaussian noise. We show that…
Best Arm Identification for Cascading Bandits in the Fixed Confidence Setting
Zixin Zhong, Wang Chi Cheung, Vincent Y. F. Tan
We design and analyze CascadeBAI, an algorithm for finding the best set of items, also called an arm, within the framework of cascading bandits. An upper bound on the time comp…