Sparse Deep Nonnegative Matrix Factorization by Zhenxing Guo, Shihua Zhang

Subjects: Get full text

An Accelerated Successive Convex Approximation Scheme With Exact Step Sizes for L1-Regression by Lukas Schynol, Moritz Hemsing, Marius Pesavento

“…We demonstrate this scheme by devising three related accelerated algorithms with provable convergence. The first introduces an additional descent step along the past optimization trajectory in the variable update that is inspired by Nesterov's accelerated gradient method and uses a closed-form step size. …”
Get full text