NeurIPS 2020

Improving Online Rent-or-Buy Algorithms with Sequential Decision Making and ML Predictions

Meta Review

The paper studies online rent-or-buy problems (ski-rental problem and the dynamic TCP problem) as a sequential decision making problem. It is shown how one can integrate predictions, typically coming from a machine learning algorithm, into this framework using a multiplicative weight algorithm. The paper has been positively evaluated by all the reviewers, with a uniform score of 6. The reviewers liked the overall idea of using ML predictions to improve the performance of online algorithms while still keeping the worst case guarantees, as well as incorporation of the multiplicative weights algorithm. On the other hand, the novelty of the paper seems a bit weak from a methodological perspective: the authors apply a well-known Hedge algorithm with ML predictions just incorporated within the prior. Also, contribution comparing to [13] seems somewhat incremental. Finally, the computational experiments do not seem clear and useful.