paper-with-me

홈 › Papers

Riemannian Perspective on Matrix Factorization

2021-02-01 · Kwangjun Ahn, Felipe Suarez

We study the non-convex matrix factorization approach to matrix completion via Riemannian geometry. Based on an optimization formulation over a Grassmannian manifold, we characterize the landscape based on the notion of principal angles between subspaces. For the fully observed case, our results show that there is a region in which the cost is geodesically convex, and outside of which all critical points are strictly saddle. We empirically study the partially observed case based on our findings.

📄 PDF Abstract BibTeX arXiv:2102.00937

Code (0)

등록된 구현이 없습니다.

Tasks

Matrix Completion

Similar Papers 제목 키워드 기반

Nonconvex Matrix Factorization is Geodesically Convex: Global Landscape Analysis for Fixed-rank Matrix Optimization From a Riemannian Perspective

2022-09-29 · Yuetian Luo, Nicolas Garcia Trillos

We study a general matrix optimization problem with a fixed-rank positive semidefinite (PSD) constraint. We perform the Burer-Monteiro factorization and consider a particular Riemannian quotient geometry in a search spac…

A Unified Framework for Structured Low-rank Matrix Learning

2018-07-01 · ICML 2018 7 · Pratik Jawanpuria, Bamdev Mishra

We consider the problem of learning a low-rank matrix, constrained to lie in a linear subspace, and introduce a novel factorization for modeling such matrices. A salient feature of the proposed factorization scheme …

Matrix CompletionMulti-Task LearningRecommendation Systems

Structured low-rank matrix learning: algorithms and applications

2017-04-24 · Pratik Jawanpuria, Bamdev Mishra

We consider the problem of learning a low-rank matrix, constrained to lie in a linear subspace, and introduce a novel factorization for modeling such matrices. A salient feature of the proposed factorization scheme is it…

Matrix CompletionMulti-Task Learning

Fixed-rank matrix factorizations and Riemannian low-rank optimization

2012-09-03 · B. Mishra, G. Meyer, S. Bonnabel, R. Sepulchre

Motivated by the problem of learning a linear regression model whose parameter is a large fixed-rank non-symmetric matrix, we consider the optimization of a smooth cost function defined on the set of fixed-rank matrices.…

Low-Rank Matrix CompletionMatrix Completion

Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry

2024-07-15 · Ziheng Chen, Yue Song, Xiao-Jun Wu, Gaowen Liu 외

Global Covariance Pooling (GCP) has been demonstrated to improve the performance of Deep Neural Networks (DNNs) by exploiting second-order statistics of high-level representations. GCP typically performs classification o…