Distributed Learning over Networks with Non-Smooth Regularizers and Feature Partitioning

Abstract

We develop a new algorithm for distributed learning with non-smooth regularizers and feature partitioning. To this end, we transform the underlying optimization problem into a suitable dual form and solve it using the alternating direction method of multipliers. The proposed algorithm is fully-distributed and does not require the conjugate function of any non-smooth regularizer function, which may be unfeasible or computationally inefficient to acquire. Numerical experiments demonstrate the effectiveness of the proposed algorithm.