稀疏矩阵分解

Nov, 2013

Sparse Matrix Factorization

Behnam Neyshabur, Rina Panigrahy

TL;DR该研究探讨如何将矩阵分解为多个稀疏矩阵，提出了一种在随机性和稀疏性假设下的算法，该算法能够恢复深度学习网络中各层之间边的结构、隐藏单元的值，矩阵分解、稀疏恢复、字典学习与深度学习之间具有密切关联。

Abstract

We investigate the problem of factorizing a matrix into several sparse matrices and propose an algorithm for this under randomness and sparsity assumptions. This problem can be viewed as a simplification of the <