# Global convergence of splitting methods for nonconvex composite optimization

arXiv: https://arxiv.org/abs/1407.0753 · HTML: https://mlsanity.com/paper/1407.0753/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2014.

## Built on by (most cited first, 19 of 19)

- [FedADMM: A Federated Primal-Dual Algorithm Allowing Partial Participation](https://mlsanity.com/paper/2203.15104/) (2022)
- [FedDR -- Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimization](https://mlsanity.com/paper/2103.03452/) (2021)
- [Convergence of Random Reshuffling Under The Kurdyka-Lojasiewicz Inequality](https://mlsanity.com/paper/2110.04926/) (2021)
- [Provably Convergent Plug-and-Play Quasi-Newton Methods](https://mlsanity.com/paper/2303.07271/) (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)
- [A Provably Convergent Information Bottleneck Solution via ADMM](https://mlsanity.com/paper/2102.04729/) (2021)
- [Convergence of the Chambolle-Pock Algorithm in the Absence of Monotonicity](https://mlsanity.com/paper/2312.06540/) (2023)
- [Joint learning of multiple Granger causal networks via non-convex regularizations: Inference of group-level brain connectivity](https://mlsanity.com/paper/2105.07196/) (2021)
- [Federated Composite Saddle Point Optimization](https://mlsanity.com/paper/2305.15643/) (2023)
- [MKL-L0/1-SVM](https://mlsanity.com/paper/2308.12016/) (2023)
- [Sparse Index Tracking: Simultaneous Asset Selection and Capital Allocation via ℓ0-Constrained Portfolio](https://mlsanity.com/paper/2309.10152/) (2023)
- [ADMM for Structured Fractional Minimization](https://mlsanity.com/paper/2411.07496/) (2024)
- [Stochastic Gradient Descent Revisited](https://mlsanity.com/paper/2412.06070/) (2024)
- [Accelerating Spectral Clustering under Fairness Constraints](https://mlsanity.com/paper/2506.08143/) (2025)
- [Douglas-Rachford Splitting for Group-Sparse Feedback Linear-Quadratic Control](https://mlsanity.com/paper/2507.19895/) (2025)
- [LRTuckerRep: Low-rank Tucker Representation Model for Multi-dimensional Data Completion](https://mlsanity.com/paper/2508.03755/) (2025)
- [DualHash: A Stochastic Primal-Dual Algorithm with Theoretical Guarantee for Deep Hashing](https://mlsanity.com/paper/2510.18218/) (2025)
- [Dynamic Proximal Gradient Algorithms for Schatten-p Quasi-Norm Regularized Problems](https://mlsanity.com/paper/2603.00333/) (2026)

## Abstract (arXiv)

We consider the problem of minimizing the sum of a smooth function h with a bounded Hessian, and a nonsmooth function. We assume that the latter function is a composition of a proper closed function P and a surjective linear map cal M, with the proximal mappings of τ P, τ > 0, simple to compute. This problem is nonconvex in general and encompasses many important applications in engineering and machine learning. In this paper, we examined two types of splitting methods for solving this nonconvex optimization problem: alternating direction method of multipliers and proximal gradient algorithm. For the direct adaptation of the alternating direction method of multipliers, we show that, if the penalty parameter is chosen sufficiently large and the sequence generated has a cluster point, then it gives a stationary point of the nonconvex problem. We also establish convergence of the whole sequence under an additional assumption that the functions h and P are semi-algebraic. Furthermore, we give simple sufficient conditions to guarantee boundedness of the sequence generated. These conditions can be satisfied for a wide range of applications including the least squares problem with the ℓ1/2 regularization. Finally, when cal M is the identity so that the proximal gradient algorithm can be efficiently applied, we show that any cluster point is stationary under a slightly more flexible constant step-size rule than what is known in the literature for a nonconvex h.