NeurIPS 2020poster18 citations
Improving Online Rent-or-Buy Algorithms with Sequential Decision Making and ML Predictions
Abstract
In this work we study online rent-or-buy problems as a sequential decision making problem. We show how one can integrate predictions, typically coming from a machine learning (ML) setup, into this framework. Specifically, we consider the ski-rental problem and the dynamic TCP acknowledgment problem. We present new online algorithms and obtain explicit performance bounds in-terms of the accuracy of the prediction. Our algorithms are close to optimal with accurate predictions while hedging against less accurate predictions.
BibTeX
@inproceedings{NEURIPS2020_f12a6a74,
author = {Banerjee, Shom},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {21072--21080},
publisher = {Curran Associates, Inc.},
title = {Improving Online Rent-or-Buy Algorithms with Sequential Decision Making and ML Predictions},
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/f12a6a7477077af66212ef0813bcf332-Paper.pdf},
volume = {33},
year = {2020}
}