Faster First-Order Methods for Stochastic Non-Convex Optimization on Riemannian Manifolds

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...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence Jg. 43; H. 2; S. 459 - 472
Hauptverfasser:	Zhou, Pan, Yuan, Xiao-Tong, Yan, Shuicheng, Feng, Jiashi
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 01.02.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Algorithms Complexity Complexity theory Computational geometry Convergence Convex analysis Convexity Machine learning Manifolds Minimization non-convex optimization online learning Optimization Principal components analysis Riemann manifold Riemannian optimization Signal processing algorithms Stochastic processes stochastic variance-reduced algorithm
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!