Loading...
conference paper
Sparse projections onto the simplex
2013
Proceedings of the 30th International Conference on Machine Learning (ICML), 2013
Most learning methods with rank or sparsity constraints use convex relaxations, which lead to optimization with the nuclear norm or the`1-norm. However, several important learning applications cannot benet 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 ecient 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.
Loading...
Name
1206.1529v5.pdf
Access type
openaccess
Size
784.14 KB
Format
Adobe PDF
Checksum (MD5)
d50e44e091b0efbd034c0f65c94ea29d