Search Results for author: B. Mishra

Found 5 papers, 0 papers with code

R3MC: A Riemannian three-factor algorithm for low-rank matrix completion

no code implementations11 Jun 2013 B. Mishra, R. Sepulchre

We exploit the versatile framework of Riemannian optimization on quotient manifolds to develop R3MC, a nonlinear conjugate-gradient method for low-rank matrix completion.

Low-Rank Matrix Completion Riemannian optimization

Fixed-rank matrix factorizations and Riemannian low-rank optimization

no code implementations3 Sep 2012 B. Mishra, G. Meyer, S. Bonnabel, R. Sepulchre

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 Completion

Low-rank optimization with trace norm penalty

no code implementations11 Dec 2011 B. Mishra, G. Meyer, F. Bach, R. Sepulchre

The fixed-rank optimization is characterized by an efficient factorization that makes the trace norm differentiable in the search space and the computation of duality gap numerically tractable.

Low-Rank Matrix Completion

Cannot find the paper you are looking for? You can Submit a new open access paper.