Second-order Online Nonconvex Optimization
From MaRDI portal
Publication:6333602
DOI10.1109/TAC.2020.3040372arXiv2001.10114MaRDI QIDQ6333602FDOQ6333602
Iman Shames, Joshua A. Taylor, Antoine Lesage-Landry
Publication date: 27 January 2020
Abstract: We present the online Newton's method, a single-step second-order method for online nonconvex optimization. We analyze its performance and obtain a dynamic regret bound that is linear in the cumulative variation between round optima. We show that if the variation between round optima is limited, the method leads to a constant regret bound. In the general case, the online Newton's method outperforms online convex optimization algorithms for convex functions and performs similarly to a specialized algorithm for strongly convex functions. We simulate the performance of the online Newton's method on a nonlinear, nonconvex moving target localization example and find that it outperforms a first-order approach.
This page was built for publication: Second-order Online Nonconvex Optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6333602)
