English

Riemannian stochastic quasi-Newton algorithm with variance reduction and its convergence analysis

Machine Learning 2017-09-19 v3 Numerical Analysis Numerical Analysis Optimization and Control Machine Learning

Abstract

Stochastic variance reduction algorithms have recently become popular for minimizing the average of a large, but finite number of loss functions. The present paper proposes a Riemannian stochastic quasi-Newton algorithm with variance reduction (R-SQN-VR). The key challenges of averaging, adding, and subtracting multiple gradients are addressed with notions of retraction and vector transport. We present convergence analyses of R-SQN-VR on both non-convex and retraction-convex functions under retraction and vector transport operators. The proposed algorithm is evaluated on the Karcher mean computation on the symmetric positive-definite manifold and the low-rank matrix completion on the Grassmann manifold. In all cases, the proposed algorithm outperforms the state-of-the-art Riemannian batch and stochastic gradient algorithms.

Keywords

Cite

@article{arxiv.1703.04890,
  title  = {Riemannian stochastic quasi-Newton algorithm with variance reduction and its convergence analysis},
  author = {Hiroyuki Kasai and Hiroyuki Sato and Bamdev Mishra},
  journal= {arXiv preprint arXiv:1703.04890},
  year   = {2017}
}
R2 v1 2026-06-22T18:45:39.235Z