AC-Band: A Combinatorial Bandit-Based Approach to Algorithm Configuration

TL;DR

AC-Band is a novel algorithm configuration method that combines theoretical guarantees with practical efficiency, outperforming existing approaches in speed while maintaining high-quality results.

Contribution

We introduce AC-Band, a bandit-based approach that bridges the gap between theoretical guarantees and practical performance in algorithm configuration.

Findings

AC-Band requires less computation time than existing methods with guarantees.

AC-Band achieves high-quality configurations comparable to heuristic methods.

The approach balances theoretical rigor with practical efficiency.

Abstract

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.