Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification

Published in Advances in Neural Information Processing Systems (NeurIPS), 2022

This paper develops minimax optimal algorithms for fixed-budget best arm identification. We provide theoretical guarantees showing that our algorithms achieve optimal sample complexity bounds, and demonstrate their effectiveness through both theoretical analysis and practical implementations.

Download paper here

Recommended citation: Komiyama, J., Tsuchiya, T., & Honda, J. (2022). “Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification.” In Advances in Neural Information Processing Systems (NeurIPS 2022).

Recommended citation: Komiyama, J., Tsuchiya, T., & Honda, J. (2022). "Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification." In Advances in Neural Information Processing Systems (NeurIPS 2022).
Download Paper