Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits

1 code implementation • 31 Jan 2023 • Yunlong Hou, Vincent Y. F. Tan, Zixin Zhong

Under this constraint, we design and analyze an algorithm {\sc PASCombUCB} that minimizes the regret over the horizon of time $T$.

Recommendation Systems

Almost Optimal Variance-Constrained Best Arm Identification

1 code implementation • 25 Jan 2022 • Yunlong Hou, Vincent Y. F. Tan, Zixin Zhong

We design and analyze VA-LUCB, a parameter-free algorithm, for identifying the best arm under the fixed-confidence setup and under a stringent constraint that the variance of the chosen arm is strictly smaller than a given threshold.