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

arXiv: https://arxiv.org/abs/2212.00333 · HTML: https://mlsanity.com/paper/2212.00333/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 43 references that are in the map.
- First posted on arXiv 1 Dec 2022.

## Builds on (most cited first, 18 of 18)

- [Non-stochastic Best Arm Identification and Hyperparameter Optimization](https://mlsanity.com/paper/1502.07943/) (2015)
- [On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice](https://mlsanity.com/paper/2007.15745/) (2020)
- [Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges](https://mlsanity.com/paper/2107.05847/) (2021)
- [Preference-based Online Learning with Dueling Bandits: A Survey](https://mlsanity.com/paper/1807.11398/) (2018)
- [ParamILS: An Automatic Algorithm Configuration Framework](https://mlsanity.com/paper/1401.3492/) (2014)
- [A Survey of Methods for Automated Algorithm Configuration](https://mlsanity.com/paper/2202.01651/) (2022)
- [How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design](https://mlsanity.com/paper/1908.02894/) (2019)
- [Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedback](https://mlsanity.com/paper/2101.08534/) (2021)
- [Bandits with many optimal arms](https://mlsanity.com/paper/2103.12452/) (2021)
- [Pure Exploration in Infinitely-Armed Bandit Models with Fixed-Confidence](https://mlsanity.com/paper/1803.04665/) (2018)
- [LeapsAndBounds: A Method for Approximately Optimal Algorithm Configuration](https://mlsanity.com/paper/1807.00755/) (2018)
- [Refined bounds for algorithm configuration: The knife-edge of dual class approximability](https://mlsanity.com/paper/2006.11827/) (2020)
- [Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration](https://mlsanity.com/paper/1902.05454/) (2019)
- [On Performance Estimation in Automatic Algorithm Configuration](https://mlsanity.com/paper/1911.08200/) (2019)
- [Bayesian Optimization With Censored Response Data](https://mlsanity.com/paper/1310.1947/) (2013)
- [Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budget](https://mlsanity.com/paper/2202.04487/) (2022)
- [On the Impact of the Cutoff Time on the Performance of Algorithm Configurators](https://mlsanity.com/paper/1904.06230/) (2019)
- [Analysis of the Performance of Algorithm Configurators for Search Heuristics with Global Mutation Operators](https://mlsanity.com/paper/2004.04519/) (2020)

## Built on by (most cited first, 6 of 6)

- [Utilitarian Algorithm Configuration for Infinite Parameter Spaces](https://mlsanity.com/paper/2405.18246/) (2024)
- [Utilitarian Algorithm Configuration](https://mlsanity.com/paper/2310.20401/) (2023)
- [Identifying Copeland Winners in Dueling Bandits with Indifferences](https://mlsanity.com/paper/2310.00750/) (2023)
- [Practical, Utilitarian Algorithm Configuration](https://mlsanity.com/paper/2510.14683/) (2025)
- [Provably Reduced Sample Cost in Prior-Guided Hyperparameter Optimization](https://mlsanity.com/paper/2606.04866/) (2026)
- [DGA2D: Directed Graph-Guided Automated Algorithm Design with Large Language Models](https://mlsanity.com/paper/2608.00700/) (2026)

## Abstract (arXiv)

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.