English

Sparse projections onto the simplex

Machine Learning 2013-04-11 v5 Machine Learning

Abstract

Most learning methods with rank or sparsity constraints use convex relaxations, which lead to optimization with the nuclear norm or the 1\ell_1-norm. However, several important learning applications cannot benefit from this approach as they feature these convex norms as constraints in addition to the non-convex rank and sparsity constraints. In this setting, we derive efficient sparse projections onto the simplex and its extension, and illustrate how to use them to solve high-dimensional learning problems in quantum tomography, sparse density estimation and portfolio selection with non-convex constraints.

Keywords

Cite

@article{arxiv.1206.1529,
  title  = {Sparse projections onto the simplex},
  author = {Anastasios Kyrillidis and Stephen Becker and Volkan Cevher and and Christoph Koch},
  journal= {arXiv preprint arXiv:1206.1529},
  year   = {2013}
}

Comments

9 Pages

R2 v1 2026-06-21T21:15:47.159Z