DeepAI AI Chat
Log In Sign Up

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

by   Jasmin Brandt, et al.

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.


page 1

page 2

page 3

page 4


Value Directed Exploration in Multi-Armed Bandits with Structured Priors

Multi-armed bandits are a quintessential machine learning problem requir...

On Performance Estimation in Automatic Algorithm Configuration

Over the last decade, research on automated parameter tuning, often refe...

Be Greedy in Multi-Armed Bandits

The Greedy algorithm is the simplest heuristic in sequential decision pr...

Action Centered Contextual Bandits

Contextual bandits have become popular as they offer a middle ground bet...

Multi-Player Bandits Models Revisited

Multi-player Multi-Armed Bandits (MAB) have been extensively studied in ...

Efficient Algorithms for Extreme Bandits

In this paper, we contribute to the Extreme Bandit problem, a variant of...

Iterative Deepening Hyperband

Hyperparameter optimization (HPO) is concerned with the automated search...