Skip to yearly menu bar Skip to main content


Customizing ML Predictions for Online Algorithms

Keerti Anand · Rong Ge · Debmalya Panigrahi

Keywords: [ Combinatorial Optimization ] [ Computational Learning Theory ] [ Optimization - General ]


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.

Chat is not available.