Faster first-order methods for stochastic non-convex optimization on Riemannian manifolds

• Main Authors: ZHOU, Pan, YUAN, Xiao-Tong, YAN, Shuicheng, FENG, Jiashi
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2019
• Subjects: Riemannian Optimization; Stochastic Variance-Reduced Algorithm; Non-convex Optimization; Online Lear; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/8990; https://ink.library.smu.edu.sg/context/sis_research/article/9993/viewcontent/2019_TPAMI_manifold.pdf
• Institution: Singapore Management University

First-order non-convex Riemannian optimization algorithms have gained recent popularity in structured machine learning problems including principal component analysis and low-rank matrix completion. The current paper presents an efficient Riemannian Stochastic Path Integrated Differential EstimatoR...