DACBench: A Benchmark Library for Dynamic Algorithm Configuration

TL;DR

DACBench is a standardized, flexible library that consolidates and facilitates benchmarking of dynamic algorithm configuration methods across various AI domains, promoting reproducibility and extensibility.

Contribution

It introduces DACBench, a comprehensive benchmark library that standardizes existing DAC benchmarks and provides a template for new ones, addressing compatibility and reproducibility issues.

Findings

Six initial benchmarks compared across difficulty dimensions

DACBench demonstrates broad applicability of DAC methods

Challenges in DAC benchmarking are highlighted

Abstract

Dynamic Algorithm Configuration (DAC) aims to dynamically control a target algorithm's hyperparameters in order to improve its performance. Several theoretical and empirical results have demonstrated the benefits of dynamically controlling hyperparameters in domains like evolutionary computation, AI Planning or deep learning. Replicating these results, as well as studying new methods for DAC, however, is difficult since existing benchmarks are often specialized and incompatible with the same interfaces. To facilitate benchmarking and thus research on DAC, we propose DACBench, a benchmark library that seeks to collect and standardize existing DAC benchmarks from different AI domains, as well as provide a template for new ones. For the design of DACBench, we focused on important desiderata, such as (i) flexibility, (ii) reproducibility, (iii) extensibility and (iv) automatic documentation and visualization. To show the potential, broad applicability and challenges of DAC, we explore how a set of six initial benchmarks compare in several dimensions of difficulty.