Provable Non-convex Optimization for Machine Learning Problems

Established: April 4, 2014

In this work, we explore theoretical properties of simple non-convex optimization methods for problems that feature prominently in several important areas such as recommendation systems, compressive sensing, computer vision etc.

Monographs:

Non-convex Optimization for Machine Learning
Foundations and Trends in Machine Learning, Official Site, Arxiv

Talks:

Provable Non-convex Optimization for Machine Learning
Summer School on Non-convex Optimization, IIT Bombay, 2015 [part 1] [part 2]
Iterative Hard Thresholding for Sparse/Low-rank Linear Regression [PDF]
INRIA, France, 2015
Iterative Hard Thresholding for Robust Regression
ITW, 2015
Provable Alternating Minimization Methods for Non-convex Optimization [PDF]
IISC Bangalore, January 2014
Provable Alternating Minimization methods for Low-rank Matrix Estimation Problems [PDF]
ICML, 2014