Details
| Original language | English |
|---|---|
| Number of pages | 3 |
| Publication status | E-pub ahead of print - 16 Dec 2020 |
Abstract
Keywords
- cs.LG, cs.NE, stat.ML
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2020.
Research output: Working paper/Preprint › Preprint
}
TY - UNPB
T1 - Squirrel
T2 - A Switching Hyperparameter Optimizer
AU - Awad, Noor
AU - Shala, Gresa
AU - Deng, Difan
AU - Mallik, Neeratyoy
AU - Feurer, Matthias
AU - Eggensperger, Katharina
AU - Biedenkapp, André
AU - Vermetten, Diederick
AU - Wang, Hao
AU - Doerr, Carola
AU - Lindauer, Marius
AU - Hutter, Frank
PY - 2020/12/16
Y1 - 2020/12/16
N2 - 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.
AB - 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.
KW - cs.LG
KW - cs.NE
KW - stat.ML
M3 - Preprint
BT - Squirrel
ER -