Skip to main content

Customizing ML predictions for online algorithms

Publication ,  Conference
Anand, K; Ge, R
Published in: 37th International Conference on Machine Learning, ICML 2020
January 1, 2020

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 blackbox, 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 signifcantly better performance, while maintaining a worst-case adversarial result when the advice is completely wrong. We support this fnding both through theoretical bounds and numerical simulations.

Duke Scholars

Published In

37th International Conference on Machine Learning, ICML 2020

ISBN

9781713821120

Publication Date

January 1, 2020

Volume

PartF168147-1

Start / End Page

280 / 290
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Anand, K., & Ge, R. (2020). Customizing ML predictions for online algorithms. In 37th International Conference on Machine Learning, ICML 2020 (Vol. PartF168147-1, pp. 280–290).
Anand, K., and R. Ge. “Customizing ML predictions for online algorithms.” In 37th International Conference on Machine Learning, ICML 2020, PartF168147-1:280–90, 2020.
Anand K, Ge R. Customizing ML predictions for online algorithms. In: 37th International Conference on Machine Learning, ICML 2020. 2020. p. 280–90.
Anand, K., and R. Ge. “Customizing ML predictions for online algorithms.” 37th International Conference on Machine Learning, ICML 2020, vol. PartF168147-1, 2020, pp. 280–90.
Anand K, Ge R. Customizing ML predictions for online algorithms. 37th International Conference on Machine Learning, ICML 2020. 2020. p. 280–290.

Published In

37th International Conference on Machine Learning, ICML 2020

ISBN

9781713821120

Publication Date

January 1, 2020

Volume

PartF168147-1

Start / End Page

280 / 290