Customizing ML Predictions for Online Algorithms
Abstract
A popular line of recent research incorporates ML advice in the design of online algorithms to improve their performance in typical instances. These papers treat the ML algorithm as a black-box, and redesign online algorithms to take advantage of ML predictions. In this paper, we ask the complementary question: can we redesign ML algorithms to provide better predictions for online algorithms? We explore this question in the context of the classic rent-or-buy problem, and show that incorporating optimization benchmarks in ML loss functions leads to significantly better performance, while maintaining a worst-case adversarial result when the advice is completely wrong. We support this finding both through theoretical bounds and numerical simulations.
Cite
Text
Anand et al. "Customizing ML Predictions for Online Algorithms." International Conference on Machine Learning, 2020.Markdown
[Anand et al. "Customizing ML Predictions for Online Algorithms." International Conference on Machine Learning, 2020.](https://mlanthology.org/icml/2020/anand2020icml-customizing/)BibTeX
@inproceedings{anand2020icml-customizing,
title = {{Customizing ML Predictions for Online Algorithms}},
author = {Anand, Keerti and Ge, Rong and Panigrahi, Debmalya},
booktitle = {International Conference on Machine Learning},
year = {2020},
pages = {303-313},
volume = {119},
url = {https://mlanthology.org/icml/2020/anand2020icml-customizing/}
}