Section: New Results

Block Coordinate Approach for Sparse Logistic Regression

Participants: Emilie Chouzenoux and Jean-Christophe Pesquet (in collaboration with G. Chierchia, Univ. Paris Est, L. M. Briceno-Arias, CMM - Univ. Chile, and A. Cherni, PhD student, Univ. Strasbourg)

We propose in [20], [33] stochastic optimization algorithms for logistic regression based on a randomized version of Douglas–Rachford splitting method. Our approach sweeps the training set by randomly selecting a mini-batch of data at each iteration, and it performs the update step by leveraging the proximity operator of the logistic loss, for which a closed-form expression is derived. Experiments carried out on standard datasets compare the efficiency of our algorithm to stochastic gradient-like methods.