no code implementations • 11 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.
no code implementations • 24 Apr 2013 • B. Mishra, G. Meyer, R. Sepulchre
The focus is on high-dimensional problems.
no code implementations • 3 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.