research
∙
11/02/2022
Gradient Descent and the Power Method: Exploiting their connection to find the leftmost eigen-pair and escape saddle points
This work shows that applying Gradient Descent (GD) with a fixed step si...
share
research
∙
06/01/2022
Stochastic Gradient Methods with Preconditioned Updates
This work considers non-convex finite sum minimization. There are a numb...
research
∙
06/06/2020
SONIA: A Symmetric Blockwise Truncated Optimization Algorithm
This work presents a new algorithm for empirical risk minimization. The ...
research
∙
06/08/2015
Linear Convergence of the Randomized Feasible Descent Method Under the Weak Strong Convexity Assumption
In this paper we generalize the framework of the feasible descent method...
research
∙
08/30/2013
Separable Approximations and Decomposition Methods for the Augmented Lagrangian
In this paper we study decomposition methods based on separable approxim...
research
∙
04/19/2013