Incremental Majorization-Minimization Optimization with Application to Large-Scale Machine Learning

TL;DR

This paper introduces an incremental majorization-minimization algorithm tailored for large-scale machine learning, providing convergence guarantees and demonstrating competitive performance on logistic regression and sparse estimation tasks.

Contribution

It develops a novel incremental MM scheme with convergence guarantees for non-convex and convex problems, applicable to large-scale machine learning.

Findings

Convergence guarantees for non-convex and convex optimization.

Linear convergence rate for strongly convex functions.

Competitive performance on logistic regression and sparse estimation.

Abstract

Majorization-minimization algorithms consist of successively minimizing a sequence of upper bounds of the objective function. These upper bounds are tight at the current estimate, and each iteration monotonically drives the objective function downhill. Such a simple principle is widely applicable and has been very popular in various scientific fields, especially in signal processing and statistics. In this paper, we propose an incremental majorization-minimization scheme for minimizing a large sum of continuous functions, a problem of utmost importance in machine learning. We present convergence guarantees for non-convex and convex optimization when the upper bounds approximate the objective up to a smooth error; we call such upper bounds "first-order surrogate functions". More precisely, we study asymptotic stationary point guarantees for non-convex problems, and for convex ones, we provide convergence rates for the expected objective function value. We apply our scheme to composite optimization and obtain a new incremental proximal gradient algorithm with linear convergence rate for strongly convex functions. In our experiments, we show that our method is competitive with the state of the art for solving machine learning problems such as logistic regression when the number of training samples is large enough, and we demonstrate its usefulness for sparse estimation with non-convex penalties.