We study the problem of online decision-making with predictions.

A recent trend in online algorithms has seen the use of future predictions generated by ML techniques to bypass pessimistic worst-case lower bounds.

Traditional online algorithms typically assume a small bid setting, where the maximumbid-to-budgetratio(κ)isinfinitesimallysmall.

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.

We study a general form of Smoothed Online Convex Optimization, a.k.a.

We study the problem of augmenting online algorithms with machine learned (ML) advice. In particular, we consider the \emph{multi-shop ski rental} (MSSR) problem, which is a generalization of the classical ski rental problem. In MSSR, each shop has different prices for buying and renting a pair of skis, and a skier has to make decisions on when and where to buy. We obtain both deterministic and randomized online algorithms with provably improved performance when either a single or multiple ML predictions are used to make decisions. These online algorithms have no knowledge about the quality or the prediction error type of the ML prediction. The performance of these online algorithms are robust to the poor performance of the predictors, but improve with better predictions. Extensive experiments using both synthetic and real world data traces verify our theoretical observations and show better performance against algorithms that purely rely on online decision making.

In this work we study the problem of using machine-learned predictions to improve performance of online algorithms. We consider two classical problems, ski rental and non-clairvoyant job scheduling, and obtain new online algorithms that use predictions to make their decisions. These algorithms are oblivious to the performance of the predictor, improve with better predictions, but do not degrade much if the predictions are poor.

We illustrate the online optimization process of RCL in Figure 1. We set b = 10 and A = I for the cost function in Eqn. The testing process is almost instant and takes less than 1 second. It does not use robustification during online optimization. By Theorem 4.1, there is a trade-off (governed by ML predictions for those problem instances that are adversarial to ROBD.