Algorithmic Regularization in Model-Free Overparametrized Asymmetric Matrix Factorization

DOI10.1137/22m1519833arXiv2203.02839OpenAlexW4385765114MaRDI QIDQ6136234

Yudong Chen, Lijun Ding, Liwei Jiang

Publication date: 29 August 2023

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2203.02839

zbMATH Keywords

overparametrizationgradient descentmodel-freeasymmetric matrix factorizationsmall initialization

Mathematics Subject Classification ID

Applications of mathematical programming (90C90) General topics in artificial intelligence (68T01)

Related Items (1)

Algorithmic Regularization in Model-Free Overparametrized Asymmetric Matrix Factorization

Cites Work

• Matrix estimation by universal singular value thresholding
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• When do neural networks outperform kernel methods?*
• Beyond Procrustes: Balancing-Free Gradient Descent for Asymmetric Low-Rank Matrix Sensing
• Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• Algorithmic Regularization in Model-Free Overparametrized Asymmetric Matrix Factorization

This page was built for publication: Algorithmic Regularization in Model-Free Overparametrized Asymmetric Matrix Factorization