Skip to yearly menu bar Skip to main content


Best Arm Identification with Resource Constraints

ZITIAN LI · Wang Chi Cheung

MR1 & MR2 - Number 11
[ ]
Thu 2 May 8 a.m. PDT — 8:30 a.m. PDT


Motivated by the cost heterogeneity in experimentation across different alternatives, we study the Best Arm Identification with Resource Constraints (BAIwRC) problem. The agent aims to identify the best arm under resource constraints, where resources are consumed for each arm pull. We make two novel contributions. We design and analyze the Successive Halving with Resource Rationing algorithm (SH-RR). The SH-RR achieves a near-optimal non-asymptotic rate of convergence in terms of the probability of successively identifying an optimal arm. Interestingly, we identify a difference in convergence rates between the cases of deterministic and stochastic resource consumption.

Live content is unavailable. Log in and register to view live content