3k citations · 9k across the 154 of their papers we have counts for
3 papers · 2 filters
Accelerated, Parallel and Proximal Coordinate Descent
Olivier Fercoq, Peter Richtárik
We propose a new stochastic coordinate descent method for minimizing the sum of convex functions each of which depends on a small number of coordinates only. Our method (APPROX) is…
Separable Approximations and Decomposition Methods for the Augmented Lagrangian
Rachael Tappenden, Peter Richtarik, Burak Buke
In this paper we study decomposition methods based on separable approximations for minimizing the augmented Lagrangian. In particular, we study and compare the Diagonal Quadratic A…
Inexact Coordinate Descent: Complexity and Preconditioning
Rachael Tappenden, Peter Richtárik, Jacek Gondzio
In this paper we consider the problem of minimizing a convex function using a randomized block coordinate descent method. One of the key steps at each iteration of the algorithm is…