Online Optimization with Memory and Competitive Control
From MaRDI portal
Publication:6334715
arXiv2002.05318MaRDI QIDQ6334715
Adam Wierman, Soon-Jo Chung, Yisong Yue, Yiheng Lin, Guanya Shi
Publication date: 12 February 2020
Abstract: This paper presents competitive algorithms for a novel class of online optimization problems with memory. We consider a setting where the learner seeks to minimize the sum of a hitting cost and a switching cost that depends on the previous decisions. This setting generalizes Smoothed Online Convex Optimization. The proposed approach, Optimistic Regularized Online Balanced Descent, achieves a constant, dimension-free competitive ratio. Further, we show a connection between online optimization with memory and online control with adversarial disturbances. This connection, in turn, leads to a new constant-competitive policy for a rich class of online control problems.
Has companion code repository: https://github.com/GuanyaShi/NeurIPS-2020-Online-Optimization-and-Competitive-Control
This page was built for publication: Online Optimization with Memory and Competitive Control
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6334715)
