English

Squirrel: A Switching Hyperparameter Optimizer

Machine Learning 2020-12-17 v2 Neural and Evolutionary Computing Machine Learning

Abstract

In this short note, we describe our submission to the NeurIPS 2020 BBO challenge. Motivated by the fact that different optimizers work well on different problems, our approach switches between different optimizers. Since the team names on the competition's leaderboard were randomly generated "alliteration nicknames", consisting of an adjective and an animal with the same initial letter, we called our approach the Switching Squirrel, or here, short, Squirrel.

Cite

@article{arxiv.2012.08180,
  title  = {Squirrel: A Switching Hyperparameter Optimizer},
  author = {Noor Awad and Gresa Shala and Difan Deng and Neeratyoy Mallik and Matthias Feurer and Katharina Eggensperger and Andre' Biedenkapp and Diederick Vermetten and Hao Wang and Carola Doerr and Marius Lindauer and Frank Hutter},
  journal= {arXiv preprint arXiv:2012.08180},
  year   = {2020}
}
R2 v1 2026-06-23T20:58:53.786Z