Inexact trust-region algorithms on Riemannian manifolds

Hiroyuki Kasai, Bamdev Mishra

Research output: Contribution to journalConference article

2 Citations (Scopus)

Abstract

We consider an inexact variant of the popular Riemannian trust-region algorithm for structured big-data minimization problems. The proposed algorithm approximates the gradient and the Hessian in addition to the solution of a trust-region sub-problem. Addressing large-scale finite-sum problems, we specifically propose sub-sampled algorithms with a fixed bound on sub-sampled Hessian and gradient sizes, where the gradient and Hessian are computed by a random sampling technique. Numerical evaluations demonstrate that the proposed algorithms outperform state-of-the-art Riemannian deterministic and stochastic gradient algorithms across different applications.

Original languageEnglish
Pages (from-to)4249-4260
Number of pages12
JournalAdvances in Neural Information Processing Systems
Volume2018-December
Publication statusPublished - 2018
Externally publishedYes
Event32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, Canada
Duration: 2018 Dec 22018 Dec 8

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint Dive into the research topics of 'Inexact trust-region algorithms on Riemannian manifolds'. Together they form a unique fingerprint.

  • Cite this