Back to Search Start Over

Local convergence of tensor methods

Authors :
Nikita Doikov
Yurii Nesterov
UCL - SST/ICTM/INMA - Pôle en ingénierie mathématique
UCL - SSH/LIDAM/CORE - Center for operations research and econometrics
Source :
Mathematical Programming, Vol. 193, no. 1, p. 315-336 (2022), Mathematical Programming
Publication Year :
2019

Abstract

In this paper, we study local convergence of high-order Tensor Methods for solving convex optimization problems with composite objective. We justify local superlinear convergence under the assumption of uniform convexity of the smooth component, having Lipschitz-continuous high-order derivative. The convergence both in function value and in the norm of minimal subgradient is established. Global complexity bounds for the Composite Tensor Method in convex and uniformly convex cases are also discussed. Lastly, we show how local convergence of the methods can be globalized using the inexact proximal iterations.

Details

ISSN :
00255610
Volume :
193
Issue :
1
Database :
OpenAIRE
Journal :
Mathematical programming
Accession number :
edsair.doi.dedup.....d6f0724a9969c71bb4acb1774f6b8928