# On the Convergence of Learning-based Iterative Methods for Nonconvex Inverse Problems

arXiv: https://arxiv.org/abs/1808.05331 · HTML: https://mlsanity.com/paper/1808.05331/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2018.

## Built on by (most cited first, 11 of 11)

- [Learning to Optimize: A Primer and A Benchmark](https://mlsanity.com/paper/2103.12828/) (2021)
- [A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization](https://mlsanity.com/paper/2106.07991/) (2021)
- [Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond](https://mlsanity.com/paper/2503.01210/) (2025)
- [Value-Function-based Sequential Minimization for Bi-level Optimization](https://mlsanity.com/paper/2110.04974/) (2021)
- [Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Vision](https://mlsanity.com/paper/2112.04719/) (2021)
- [DEAL: Data-Efficient Adversarial Learning for High-Quality Infrared Imaging](https://mlsanity.com/paper/2503.00905/) (2025)
- [Equilibrated Zeroth-Order Unrolled Deep Networks for Accelerated MRI](https://mlsanity.com/paper/2112.09891/) (2021)
- [Hierarchical Optimization-Derived Learning](https://mlsanity.com/paper/2302.05587/) (2023)
- [Structured Sparse Non-negative Matrix Factorization with L20-Norm for scRNA-seq Data Analysis](https://mlsanity.com/paper/2104.13171/) (2021)
- [Token-Level Uncertainty-Aware Objective for Language Model Post-Training](https://mlsanity.com/paper/2503.16511/) (2025)
- [Effective Receptive Field Ordering Matters for Infrared Small Target Detection](https://mlsanity.com/paper/2607.23994/) (2026)

## Abstract (arXiv)

Numerous tasks at the core of statistics, learning and vision areas are specific cases of ill-posed inverse problems. Recently, learning-based (e.g., deep) iterative methods have been empirically shown to be useful for these problems. Nevertheless, integrating learnable structures into iterations is still a laborious process, which can only be guided by intuitions or empirical insights. Moreover, there is a lack of rigorous analysis about the convergence behaviors of these reimplemented iterations, and thus the significance of such methods is a little bit vague. This paper moves beyond these limits and proposes Flexible Iterative Modularization Algorithm (FIMA), a generic and provable paradigm for nonconvex inverse problems. Our theoretical analysis reveals that FIMA allows us to generate globally convergent trajectories for learning-based iterative methods. Meanwhile, the devised scheduling policies on flexible modules should also be beneficial for classical numerical methods in the nonconvex scenario. Extensive experiments on real applications verify the superiority of FIMA.