Wednesday, April 24, 2019 - 2:00pm to Thursday, April 25, 2019 - 2:55pm
Event Calendar Category
Other LIDS Events
Speaker Name
Carl Olsson
Affiliation
Lund University
Building and Room number
32-D677
Abstract
Rank priors are frequently employed for regularizing ill-posed linear inverse problems. Since they are both discontinuous and non-convex they are often replaced with the nuclear norm. While the resulting formulation is easy to optimize it is also known to suffer from a shrinking bias that can severely degrade the solution in the presence of noise.
In this talk, we present a class of alternative non-convex regularization terms that do not suffer from the same bias. We show that if a restricted isometry property holds then there is typically only one low-rank stationary point. In order to derive an efficient inference algorithm, we show that when using a bilinear parameterization our regularization term can be well approximated with a quadratic function which opens up the possibility to use second-order methods such as Levenberg-Marquardt or Variable Projections. We show on several real datasets that our approach outperforms current methods both in terms of relaxation quality and convergence speed.