0.25
0.5
0.75
1.25
1.5
1.75
2
Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local optima
Published on Nov 07, 20142080 Views
We establish theoretical results concerning all local optima of various regularized M-estimators, where both loss and penalty functions are allowed to be nonconvex. Our results show that as long as th
Related categories
Chapter list
Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local optima00:00
Benefits of nonconvex regularizers00:27
How to find optima?01:31
Our contributions02:38