DeepAI AI Chat
Log In Sign Up

Customizing ML Predictions for Online Algorithms

by   Keerti Anand, et al.
Duke University

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.


page 1

page 2

page 3

page 4


Online Algorithms for Multi-shop Ski Rental with Machine Learned Predictions

We study the problem of augmenting online algorithms with machine learne...

Online TSP with Predictions

We initiate the study of online routing problems with predictions, inspi...

A New Approach to Capacity Scaling Augmented With Unreliable Machine Learning Predictions

Modern data centers suffer from immense power consumption. The erratic b...

Online Algorithms for Weighted Paging with Predictions

In this paper, we initiate the study of the weighted paging problem with...

Learning Augmented Energy Minimization via Speed Scaling

As power management has become a primary concern in modern data centers,...

Online Regenerative Learning

We study a type of Online Linear Programming (OLP) problem that maximize...