Skip to Main content Skip to Navigation
Journal articles

Fast Algorithms for Sparse Reduced-Rank Regression

Abstract : We consider a reformulation of Reduced-Rank Regression (RRR) and Sparse Reduced-Rank Regression (SRRR) as a non-convex non-differentiable function of a single of the two matrices usually introduced to parametrize low-rank matrix learning problems. We study the behavior of proximal gradient algorithms for the minimization of the objective. In particular, based on an analysis of the geometry of the problem, we establish that a proximal Polyak-Łojasiewicz inequality is satisfied in a neighborhood of the set of optima under a condition on the regularization parameter. We consequently derive linear convergence rates for the proximal gradient descent with line search and for related algorithms in a neighborhood of the optima. Our experiments show that our formulation leads to much faster learning algorithms for RRR and especially for SRRR.
Complete list of metadata

Cited literature [19 references]  Display  Hide  Download
Contributor : Benjamin Dubois Connect in order to contact the contributor
Submitted on : Friday, March 22, 2019 - 9:17:25 AM
Last modification on : Saturday, January 15, 2022 - 3:59:27 AM
Long-term archiving on: : Sunday, June 23, 2019 - 12:33:19 PM



  • HAL Id : hal-02075623, version 1


Benjamin Dubois, Jean-François Delmas, Guillaume Obozinski. Fast Algorithms for Sparse Reduced-Rank Regression. Proceedings of Machine Learning Research, PMLR, inPress. ⟨hal-02075623⟩



Record views


Files downloads