PRISMA: PRoximal Iterative SMoothing Algorithm
Optimization and Control
2012-11-20 v2 Machine Learning
Abstract
Motivated by learning problems including max-norm regularized matrix completion and clustering, robust PCA and sparse inverse covariance selection, we propose a novel optimization algorithm for minimizing a convex objective which decomposes into three parts: a smooth part, a simple non-smooth Lipschitz part, and a simple non-smooth non-Lipschitz part. We use a time variant smoothing strategy that allows us to obtain a guarantee that does not depend on knowing in advance the total number of iterations nor a bound on the domain.
Cite
@article{arxiv.1206.2372,
title = {PRISMA: PRoximal Iterative SMoothing Algorithm},
author = {Francesco Orabona and Andreas Argyriou and Nathan Srebro},
journal= {arXiv preprint arXiv:1206.2372},
year = {2012}
}