Riemannian gradient methods for stochastic composition problems

DOI10.1016/J.NEUNET.2022.06.004WikidataQ115342702 ScholiaQ115342702MaRDI QIDQ6488717

Feihu Huang, Shangqian Gao

Publication date: 17 October 2023

Published in: Neural Networks (Search for Journal in Brave)

zbMATH Keywords

principal component analysisRiemannian manifoldStiefel manifoldGrassmann manifolddeep neural networkscomposition optimization

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Statistics (62-XX) Differential geometry (53-XX)

Cites Work

• Lie-group-type neural system learning by manifold retractions
• Distributionally robust optimization. A review on theory and applications
• Low-Rank Matrix Completion by Riemannian Optimization
• Manopt, a Matlab toolbox for optimization on manifolds
• A Broyden Class of Quasi-Newton Methods for Riemannian Optimization
• Complete Dictionary Recovery Over the Sphere II: Recovery by Riemannian Trust-Region Method
• Empirical Arithmetic Averaging Over the Compact Stiefel Manifold
• Accelerating Stochastic Composition Optimization
• Gradient-based Learning Methods Extended to Smooth Manifolds Applied to Automated Clustering
• Riemannian Stochastic Variance Reduced Gradient Algorithm with Retraction and Vector Transport
• Solving Stochastic Compositional Optimization is Nearly as Easy as Solving Stochastic Optimization

This page was built for publication: Riemannian gradient methods for stochastic composition problems