You can manage bookmarks using lists, please log in to your user account for this.
Media type:
E-Book;
Report;
Text
Title:
Near-optimal tensor methods for minimizing gradient norm
Contributor:
Dvurechensky, Pavel
[Author];
Gasnikov, Alexander
[Author];
Ostroukhov, Petr
[Author];
Uribe, A. Cesar
[Author];
Ivanova, Anastasiya
[Author]
imprint:
Weierstrass Institute for Applied Analysis and Stochastics publication server, 2020
Footnote:
Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.
Description:
Motivated by convex problems with linear constraints and, in particular, by entropy-regularized optimal transport, we consider the problem of finding approximate stationary points, i.e. points with the norm of the objective gradient less than small error, of convex functions with Lipschitz p-th order derivatives. Lower complexity bounds for this problem were recently proposed in [Grapiglia and Nesterov, arXiv:1907.07053]. However, the methods presented in the same paper do not have optimal complexity bounds. We propose two optimal up to logarithmic factors methods with complexity bounds with respect to the initial objective residual and the distance between the starting point and solution respectively