paper-with-me

홈 › Papers

Geom-SPIDER-EM: Faster Variance Reduced Stochastic Expectation Maximization for Nonconvex Finite-Sum Optimization

2020-11-24 · Gersende Fort, Eric Moulines, Hoi-To Wai

The Expectation Maximization (EM) algorithm is a key reference for inference in latent variable models; unfortunately, its computational cost is prohibitive in the large scale learning setting. In this paper, we propose an extension of the Stochastic Path-Integrated Differential EstimatoR EM (SPIDER-EM) and derive complexity bounds for this novel algorithm, designed to solve smooth nonconvex finite-sum optimization problems. We show that it reaches the same state of the art complexity bounds as SPIDER-EM; and provide conditions for a linear rate of convergence. Numerical results support our findings.

📄 PDF Abstract BibTeX arXiv:2011.12392

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

R-SPIDER: A Fast Riemannian Stochastic Optimization Algorithm with Curvature Independent Rate

2018-11-10 · Jingzhao Zhang, Hongyi Zhang, Suvrit Sra

We study smooth stochastic optimization problems on Riemannian manifolds. Via adapting the recently proposed SPIDER algorithm \citep{fang2018spider} (a variance reduced stochastic method) to Riemannian manifold, we can a…

Stochastic Optimization

SpiderBoost and Momentum: Faster Stochastic Variance Reduction Algorithms

2018-10-25 · Zhe Wang, Kaiyi Ji, Yi Zhou, Yingbin Liang 외

SARAH and SPIDER are two recently developed stochastic variance-reduced algorithms, and SPIDER has been shown to achieve a near-optimal first-order oracle complexity in smooth nonconvex optimization. However, SPIDER uses…

Momentum Schemes with Stochastic Variance Reduction for Nonconvex Composite Optimization

2019-02-07 · Yi Zhou, Zhe Wang, Kaiyi Ji, Yingbin Liang 외

Two new stochastic variance-reduced algorithms named SARAH and SPIDER have been recently proposed, and SPIDER has been shown to achieve a near-optimal gradient oracle complexity for nonconvex optimization. However, the t…

SpiderBoost and Momentum: Faster Variance Reduction Algorithms

2019-12-01 · NeurIPS 2019 12 · Zhe Wang, Kaiyi Ji, Yi Zhou, Yingbin Liang 외

SARAH and SPIDER are two recently developed stochastic variance-reduced algorithms, and SPIDER has been shown to achieve a near-optimal first-order oracle complexity in smooth nonconvex optimization. However, SPIDER uses…

The perturbed prox-preconditioned spider algorithm: non-asymptotic convergence bounds

2021-05-25 · Gersende Fort, E Moulines

A novel algorithm named Perturbed Prox-Preconditioned SPIDER (3P-SPIDER) is introduced. It is a stochastic variancereduced proximal-gradient type algorithm built on Stochastic Path Integral Differential EstimatoR (SPIDER…