CoCoA Is ADMM: Unifying Two Paradigms in Distributed Optimization

TL;DR

This paper unifies two prominent distributed optimization algorithms, CoCoA and ADMM, revealing their fundamental connections and demonstrating how tuning parameters can enhance their performance in empirical risk minimization tasks.

Contribution

The paper shows that CoCoA and ADMM are fundamentally related and can be expressed in a unified framework, enabling improved algorithm performance through parameter tuning.

Findings

CoCoA is a special case of proximal ADMM.

Consensus ADMM is equivalent to a proximal ADMM.

Tuning augmented Lagrangian parameters improves performance.

Abstract

We consider primal-dual algorithms for general empirical risk minimization problems in distributed settings, focusing on two prominent classes of algorithms. The first class is the communication-efficient distributed dual coordinate ascent (CoCoA), derived from the coordinate ascent method for solving the dual problem. The second class is the alternating direction method of multipliers (ADMM), including consensus ADMM, proximal ADMM, and linearized ADMM. We demonstrate that both classes of algorithms can be transformed into a unified update form that involves only primal and dual variables. This discovery reveals key connections between the two classes of algorithms: CoCoA can be interpreted as a special case of proximal ADMM for solving the dual problem, while consensus ADMM is equivalent to a proximal ADMM algorithm. This discovery provides insight into how we can easily enable the ADMM variants to outperform the CoCoA variants by adjusting the augmented Lagrangian parameter. We further explore linearized versions of ADMM and analyze the effects of tuning parameters on these ADMM variants in the distributed setting. Extensive simulation studies and real-world data analysis support our theoretical findings.