AC-Band: A Combinatorial Bandit-Based Approach to Algorithm Configuration
This addresses the gap between theoretical and practical performance in automated algorithm configuration, though it appears incremental as it builds on existing bandit methods.
The paper tackles the algorithm configuration problem by introducing AC-Band, a multi-armed bandit-based approach that reduces computation time compared to other theoretically-guaranteed methods while maintaining high-quality configurations.
We study the algorithm configuration (AC) problem, in which one seeks to find an optimal parameter configuration of a given target algorithm in an automated way. Recently, there has been significant progress in designing AC approaches that satisfy strong theoretical guarantees. However, a significant gap still remains between the practical performance of these approaches and state-of-the-art heuristic methods. To this end, we introduce AC-Band, a general approach for the AC problem based on multi-armed bandits that provides theoretical guarantees while exhibiting strong practical performance. We show that AC-Band requires significantly less computation time than other AC approaches providing theoretical guarantees while still yielding high-quality configurations.