Using Predictions in Online Optimization

Niangjun Chen, Joshua Comden, Zhenhua Liu, Anshul Gandhi, Adam Wierman
2016 Proceedings of the 2016 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Science - SIGMETRICS '16  
We consider online convex optimization (OCO) problems with switching costs and noisy predictions. While the design of online algorithms for OCO problems has received considerable attention, the design of algorithms in the context of noisy predictions is largely open. To this point, two promising algorithms have been proposed: Receding Horizon Control (RHC) and Averaging Fixed Horizon Control (AFHC). The comparison of these policies is largely open. AFHC has been shown to provide better
more » ... e performance, while RHC outperforms AFHC in many realistic settings. In this paper, we introduce a new class of policies, Committed Horizon Control (CHC), that generalizes both RHC and AFHC. We provide average-case analysis and concentration results for CHC policies, yielding the first analysis of RHC for OCO problems with noisy predictions. Further, we provide explicit results characterizing the optimal CHC policy as a function of properties of the prediction noise, e.g., variance and correlation structure. Our results provide a characterization of when AFHC outperforms RHC and vice versa, as well as when other CHC policies outperform both RHC and AFHC.
doi:10.1145/2896377.2901464 dblp:conf/sigmetrics/ChenCLGW16 fatcat:x6gsq7ny4zdvlgivzo2bd26gyy