Skip to yearly menu bar Skip to main content


Bures-Wasserstein Barycenters and Low-Rank Matrix Recovery

Tyler Maunu · Thibaut Le Gouic · Philippe Rigollet

Auditorium 1 Foyer 124


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.

Live content is unavailable. Log in and register to view live content