Blackbox Optimization of Unimodal Functions
Abstract
We provide an intuitive new algorithm for blackbox stochastic optimization of unimodal functions, a function class that we observe empirically can capture hyperparameter-tuning loss surfaces. Our method’s convergence guarantee automatically adapts to Lipschitz constants and other problem difficulty parameters, recovering and extending prior results. We complement our theoretical development with experimental validation on hyperparameter tuning tasks.
Cite
Text
Cutkosky et al. "Blackbox Optimization of Unimodal Functions." Uncertainty in Artificial Intelligence, 2023.Markdown
[Cutkosky et al. "Blackbox Optimization of Unimodal Functions." Uncertainty in Artificial Intelligence, 2023.](https://mlanthology.org/uai/2023/cutkosky2023uai-blackbox/)BibTeX
@inproceedings{cutkosky2023uai-blackbox,
title = {{Blackbox Optimization of Unimodal Functions}},
author = {Cutkosky, A. and Das, A. and Kong, W. and Lee, C. and Sen, R.},
booktitle = {Uncertainty in Artificial Intelligence},
year = {2023},
pages = {476-484},
volume = {216},
url = {https://mlanthology.org/uai/2023/cutkosky2023uai-blackbox/}
}