Almost Optimal Variance-Constrained Best Arm Identification

01/25/2022
by   Yunlong Hou, et al.
0

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. An upper bound on VA-LUCB's sample complexity is shown to be characterized by a fundamental variance-aware hardness quantity H_VA. By proving a lower bound, we show that sample complexity of VA-LUCB is optimal up to a factor logarithmic in H_VA. Extensive experiments corroborate the dependence of the sample complexity on the various terms in H_VA. By comparing VA-LUCB's empirical performance to a close competitor RiskAverse-UCB-BAI by David et al. (2018), our experiments suggest that VA-LUCB has the lowest sample complexity for this class of risk-constrained best arm identification problems, especially for the riskiest instances.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset

Sign in with Google

×

Use your Google Account to sign in to DeepAI

×

Consider DeepAI Pro