Riemannian Perspective on Matrix Factorization
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Matrix CompletionSimilar Papers 제목 키워드 기반
Nonconvex Matrix Factorization is Geodesically Convex: Global Landscape Analysis for Fixed-rank Matrix Optimization From a Riemannian Perspective
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
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 SystemsStructured low-rank matrix learning: algorithms and applications
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 LearningFixed-rank matrix factorizations and Riemannian low-rank optimization
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 CompletionUnderstanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry
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…