DACBench: A Benchmark Library for Dynamic Algorithm Configuration
This provides a standardized tool for researchers in AI to benchmark DAC methods, facilitating replication and new research, though it is incremental as it builds on existing benchmarks.
The authors tackled the difficulty of replicating and studying Dynamic Algorithm Configuration (DAC) methods due to specialized and incompatible benchmarks by proposing DACBench, a benchmark library that standardizes existing benchmarks and provides a template for new ones, demonstrating its potential with six initial benchmarks.
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.