Symmetric Rank-k Methods

Authors Chengchang Liu, Cheng Chen, Luo Luo

Abstract: This paper proposes a novel class of block quasi-Newton methods for convex optimization which we call symmetric rank-

k

(SR-

k

) methods. Each iteration of SR-

k

incorporates the curvature information with

k

Hessian-vector products achieved from the greedy or random strategy. We prove SR-

k

methods have the local superlinear convergence rate of

for minimizing smooth and strongly self-concordant function, where

d

is the problem dimension and

t

is the iteration counter. This is the first explicit superlinear convergence rate for block quasi-Newton methods and it successfully explains why block quasi-Newton methods converge faster than standard quasi-Newton methods in practice.

This page was built for publication: Symmetric Rank-$k$ Methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6509390)