Work

Fast distributed coordinate descent for non-strongly convex losses

Year: 2014

Type: conference-paper

Abstract: We propose an efficient distributed randomized coordinate descent method for minimizing regularized non-strongly convex loss functions. The method attains the optimal O(1/k2) convergence rate, where k is the iteration counter. The core of the work is the theoretical study of stepsize parameters. We have implemented the method on Archer - the largest super-computer in the UK-and show that the method is capable of solving a (synthetic) LASSO optimization problem with 50 billion variables.

Source: IEEE International Workshop on Machine Learning for Signal Processing (MLSP)

DOI: 10.1109/mlsp.2014.6958862

Authors: Olivier Fercoq, Zheng Qu, Peter Richtarik, Martin Takac

Institution: University of Edinburgh

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Engineering and Physical Sciences Research Council