# Global Convergence of ADMM in Nonconvex Nonsmooth Optimization

arXiv: https://arxiv.org/abs/1511.06324 · HTML: https://mlsanity.com/paper/1511.06324/

## Key facts

- Cited by 98 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2015.

## Built on by (most cited first, 30 of 98)

- [Imitation Learning with Stability and Safety Guarantees](https://mlsanity.com/paper/2012.09293/) (2020)
- [Learning to Warm-Start Fixed-Point Optimization Algorithms](https://mlsanity.com/paper/2309.07835/) (2023)
- [Towards Federated Bayesian Network Structure Learning with Continuous Optimization](https://mlsanity.com/paper/2110.09356/) (2021)
- [ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models](https://mlsanity.com/paper/2406.07831/) (2024)
- [Convergence of Random Reshuffling Under The Kurdyka-Lojasiewicz Inequality](https://mlsanity.com/paper/2110.04926/) (2021)
- [Equal Opportunity of Coverage in Fair Regression](https://mlsanity.com/paper/2311.02243/) (2023)
- [Nonlinear Transform Induced Tensor Nuclear Norm for Tensor Completion](https://mlsanity.com/paper/2110.08774/) (2021)
- [Federated Learning and Meta Learning: Approaches, Applications, and Directions](https://mlsanity.com/paper/2210.13111/) (2022)
- [Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patterns](https://mlsanity.com/paper/2205.09390/) (2022)
- [Joint Network Topology Inference via a Shared Graphon Model](https://mlsanity.com/paper/2209.08223/) (2022)
- [Oracle Complexity of Single-Loop Switching Subgradient Methods for Non-Smooth Weakly Convex Functional Constrained Optimization](https://mlsanity.com/paper/2301.13314/) (2023)
- [Online Federated Learning via Non-Stationary Detection and Adaptation amidst Concept Drift](https://mlsanity.com/paper/2211.12578/) (2022)
- [Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization](https://mlsanity.com/paper/2305.19838/) (2023)
- [Training Recurrent Neural Networks by Sequential Least Squares and the Alternating Direction Method of Multipliers](https://mlsanity.com/paper/2112.15348/) (2021)
- [vSHARP: variable Splitting Half-quadratic Admm algorithm for Reconstruction of inverse-Problems](https://mlsanity.com/paper/2309.09954/) (2023)
- [A unifying framework for n-dimensional quasi-conformal mappings](https://mlsanity.com/paper/2110.10437/) (2021)
- [Enhanced Latent Multi-view Subspace Clustering](https://mlsanity.com/paper/2312.14763/) (2023)
- [AugFL: Augmenting Federated Learning with Pretrained Models](https://mlsanity.com/paper/2503.02154/) (2025)
- [LensNet: An End-to-End Learning Framework for Empirical Point Spread Function Modeling and Lensless Imaging Reconstruction](https://mlsanity.com/paper/2505.01755/) (2025)
- [LADMM-Net: An Unrolled Deep Network For Spectral Image Fusion From Compressive Data](https://mlsanity.com/paper/2103.00940/) (2021)
- [Multi-channel Nuclear Norm Minus Frobenius Norm Minimization for Color Image Denoising](https://mlsanity.com/paper/2209.08094/) (2022)
- [Interaction-Aware Trajectory Planning for Autonomous Vehicles with Analytic Integration of Neural Networks into Model Predictive Control](https://mlsanity.com/paper/2301.05393/) (2023)
- [Towards Certification of Uncertainty Calibration under Adversarial Attacks](https://mlsanity.com/paper/2405.13922/) (2024)
- [SAFE: Finding Sparse and Flat Minima to Improve Pruning](https://mlsanity.com/paper/2506.06866/) (2025)
- [Communication Efficient Federated Learning via Ordered ADMM in a Fully Decentralized Setting](https://mlsanity.com/paper/2202.02580/) (2022)
- [Smoothing ADMM for Sparse-Penalized Quantile Regression with Non-Convex Penalties](https://mlsanity.com/paper/2309.03094/) (2023)
- [Minimizing L1 over L2 norms on the gradient](https://mlsanity.com/paper/2101.00809/) (2021)
- [A Framework of Inertial Alternating Direction Method of Multipliers for Non-Convex Non-Smooth Optimization](https://mlsanity.com/paper/2102.05433/) (2021)
- [Hierarchical fuzzy neural networks with privacy preservation for heterogeneous big data](https://mlsanity.com/paper/2209.08467/) (2022)
- [A Riemannian ADMM](https://mlsanity.com/paper/2211.02163/) (2022)

## Abstract (arXiv)

In this paper, we analyze the convergence of the alternating direction method of multipliers (ADMM) for minimizing a nonconvex and possibly nonsmooth objective function, φ(x0,ldots,xp,y), subject to coupled linear equality constraints. Our ADMM updates each of the primal variables x0,ldots,xp,y, followed by updating the dual variable. We separate the variable y from xi's as it has a special role in our analysis. The developed convergence guarantee covers a variety of nonconvex functions such as piecewise linear functions, ℓq quasi-norm, Schatten-q quasi-norm (0<q<1), minimax concave penalty (MCP), and smoothly clipped absolute deviation (SCAD) penalty. It also allows nonconvex constraints such as compact manifolds (e.g., spherical, Stiefel, and Grassman manifolds) and linear complementarity constraints. Also, the x0-block can be almost any lower semi-continuous function. By applying our analysis, we show, for the first time, that several ADMM algorithms applied to solve nonconvex models in statistical learning, optimization on manifold, and matrix decomposition are guaranteed to converge. Our results provide sufficient conditions for ADMM to converge on (convex or nonconvex) monotropic programs with three or more blocks, as they are special cases of our model. ADMM has been regarded as a variant to the augmented Lagrangian method (ALM). We present a simple example to illustrate how ADMM converges but ALM diverges with bounded penalty parameter β. Indicated by this example and other analysis in this paper, ADMM might be a better choice than ALM for some nonconvex nonsmooth problems, because ADMM is not only easier to implement, it is also more likely to converge for the concerned scenarios.