# Fast Stochastic Alternating Direction Method of Multipliers

arXiv: https://arxiv.org/abs/1308.3558 · HTML: https://mlsanity.com/paper/1308.3558/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2013.

## Built on by (most cited first, 3 of 3)

- [Preconditioned Inexact Stochastic ADMM for Deep Model](https://mlsanity.com/paper/2502.10784/) (2025)
- [Privacy Amplification by Iteration for ADMM with (Strongly) Convex Objective Functions](https://mlsanity.com/paper/2312.08685/) (2023)
- [A General Continuous-Time Formulation of Stochastic ADMM and Its Variants](https://mlsanity.com/paper/2404.14358/) (2024)

## Abstract (arXiv)

In this paper, we propose a new stochastic alternating direction method of multipliers (ADMM) algorithm, which incrementally approximates the full gradient in the linearized ADMM formulation. Besides having a low per-iteration complexity as existing stochastic ADMM algorithms, the proposed algorithm improves the convergence rate on convex problems from O(frac 1 √T) to O(frac 1 T), where T is the number of iterations. This matches the convergence rate of the batch ADMM algorithm, but without the need to visit all the samples in each iteration. Experiments on the graph-guided fused lasso demonstrate that the new algorithm is significantly faster than state-of-the-art stochastic and batch ADMM algorithms.