Incremental Aggregated Proximal and Augmented Lagrangian Algorithms

TL;DR

This paper introduces incremental aggregated proximal and augmented Lagrangian algorithms for large-scale convex optimization, demonstrating linear convergence under certain conditions and exploring their distributed, dual, and constrained variants.

Contribution

It proposes novel incremental aggregated algorithms for convex optimization, extending proximal and augmented Lagrangian methods with convergence guarantees and applications to distributed and constrained problems.

Findings

Linear convergence under strong convexity and differentiability.

Distributed asynchronous variants with bounded delays.

Comparison with existing decomposition algorithms like ADMM.

Abstract

We consider minimization of the sum of a large number of convex functions, and we propose an incremental aggregated version of the proximal algorithm, which bears similarity to the incremental aggregated gradient and subgradient methods that have received a lot of recent attention. Under cost function differentiability and strong convexity assumptions, we show linear convergence for a sufficiently small constant stepsize. This result also applies to distributed asynchronous variants of the method, involving bounded interprocessor communication delays. We then consider dual versions of incremental proximal algorithms, which are incremental augmented Lagrangian methods for separable equality-constrained optimization problems. Contrary to the standard augmented Lagrangian method, these methods admit decomposition in the minimization of the augmented Lagrangian, and update the multipliers far more frequently. Our incremental aggregated augmented Lagrangian methods bear similarity to several known decomposition algorithms, including the alternating direction method of multipliers (ADMM) and more recent variations. We compare these methods in terms of their properties, and highlight their potential advantages and limitations. We also address the solution of separable inequality-constrained optimization problems through the use of nonquadratic augmented Lagrangiias such as the exponential, and we dually consider a corresponding incremental aggregated version of the proximal algorithm that uses nonquadratic regularization, such as an entropy function. We finally propose a closely related linearly convergent method for minimization of large differentiable sums subject to an orthant constraint, which may be viewed as an incremental aggregated version of the mirror descent method.