Bures-Wasserstein Barycenters and Low-Rank Matrix Recovery

10/26/2022
by   Tyler Maunu, et al.
0

We revisit the problem of recovering a low-rank positive semidefinite matrix from rank-one projections using tools from optimal transport. More specifically, we show that a variational formulation of this problem is equivalent to computing a Wasserstein barycenter. In turn, this new perspective enables the development of new geometric first-order methods with strong convergence guarantees in Bures-Wasserstein distance. Experiments on simulated data demonstrate the advantages of our new methodology over existing methods.

READ FULL TEXT

page 3

page 12

research
05/21/2017

Improved Algorithms for Matrix Recovery from Rank-One Projections

We consider the problem of estimation of a low-rank matrix from a limite...
research
04/27/2020

Hierarchical Low-Rank Approximation of Regularized Wasserstein distance

Sinkhorn divergence is a measure of dissimilarity between two probabilit...
research
03/06/2023

Critical Points and Convergence Analysis of Generative Deep Linear Networks Trained with Bures-Wasserstein Loss

We consider a deep matrix factorization model of covariance matrices tra...
research
11/29/2021

Local convergence of alternating low-rank optimization methods with overrelaxation

The local convergence of alternating optimization methods with overrelax...
research
11/12/2021

Approximating Optimal Transport via Low-rank and Sparse Factorization

Optimal transport (OT) naturally arises in a wide range of machine learn...
research
05/31/2023

Unbalanced Low-rank Optimal Transport Solvers

The relevance of optimal transport methods to machine learning has long ...
research
06/02/2021

Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs

The ability to compare and align related datasets living in heterogeneou...

Please sign up or login with your details

Forgot password? Click here to reset