ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool
Abstract
Algorithm configuration procedures optimize parameters of a given algorithm to perform well over a distribution of inputs. Recent theoretical work focused on the case of selecting between a small number of alternatives. In practice, parameter spaces are often very large or infinite, and so successful heuristic procedures discard parameters ``impatiently'', based on very few observations. Inspired by this idea, we introduce ImpatientCapsAndRuns, which quickly discards less promising configurations, significantly speeding up the search procedure compared to previous algorithms with theoretical guarantees, while still achieving optimal runtime up to logarithmic factors under mild assumptions. Experimental results demonstrate a practical improvement.
Cite
Text
Weisz et al. "ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool." Neural Information Processing Systems, 2020.Markdown
[Weisz et al. "ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/weisz2020neurips-impatientcapsandruns/)BibTeX
@inproceedings{weisz2020neurips-impatientcapsandruns,
title = {{ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool}},
author = {Weisz, Gellert and György, András and Lin, Wei-I and Graham, Devon and Leyton-Brown, Kevin and Szepesvari, Csaba and Lucier, Brendan},
booktitle = {Neural Information Processing Systems},
year = {2020},
url = {https://mlanthology.org/neurips/2020/weisz2020neurips-impatientcapsandruns/}
}