Inexact trust-region algorithms on Riemannian manifolds

Hiroyuki Kasai, Bamdev Mishra

研究成果: Conference article査読

9 被引用数 (Scopus)

抄録

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.

本文言語English
ページ(範囲)4249-4260
ページ数12
ジャーナルAdvances in Neural Information Processing Systems
2018-December
出版ステータスPublished - 2018
外部発表はい
イベント32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, Canada
継続期間: 2018 12月 22018 12月 8

ASJC Scopus subject areas

  • コンピュータ ネットワークおよび通信
  • 情報システム
  • 信号処理

フィンガープリント

「Inexact trust-region algorithms on Riemannian manifolds」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル