Generalized Majorization-Minimization

Sobhan Naderi Parizi, Kun He, Reza Aghajani, Stan Sclaroff, Pedro F. Felzenszwalb

Abstract: Non-convex optimization is ubiquitous in machine learning. Majorization-Minimization (MM) is a powerful iterative procedure for optimizing non-convex functions that works by optimizing a sequence o...