Sign in
FAST DISTRIBUTED COORDINATE DESCENT FOR NON-STRONGLY CONVEX LOSSES
Conference proceeding

FAST DISTRIBUTED COORDINATE DESCENT FOR NON-STRONGLY CONVEX LOSSES

Olivier Fercoq, Zheng Qu, Peter Richtarik and Martin Takac
2014 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), pp.1-6
IEEE International Workshop on Machine Learning for Signal Processing
14/11/2014

Abstract

Computer Science Computer Science, Artificial Intelligence Computer Science, Information Systems Engineering Engineering, Electrical & Electronic Science & Technology Technology
We propose an efficient distributed randomized coordinate descent method for minimizing regularized non-strongly convex loss functions. The method attains the optimal O (1 / k(2)) 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.

Metrics

1 Record Views

Details