# Data-driven nonsmooth optimization

arXiv: https://arxiv.org/abs/1808.00946 · HTML: https://mlsanity.com/paper/1808.00946/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Aug 2018.

## Built on by (most cited first, 6 of 6)

- [Tutorial on amortized optimization](https://mlsanity.com/paper/2202.00665/) (2022)
- [Graph-based Neural Acceleration for Nonnegative Matrix Factorization](https://mlsanity.com/paper/2202.00264/) (2022)
- [Deep network series for large-scale high-dynamic range imaging](https://mlsanity.com/paper/2210.16060/) (2022)
- [Unsupervised approaches based on optimal transport and convex analysis for inverse problems in imaging](https://mlsanity.com/paper/2311.08972/) (2023)
- [Deep Learning for Material Decomposition in Photon-Counting CT](https://mlsanity.com/paper/2208.03360/) (2022)
- [OpReg-Boost: Learning to Accelerate Online Algorithms with Operator Regression](https://mlsanity.com/paper/2105.13271/) (2021)

## Abstract (arXiv)

In this work, we consider methods for solving large-scale optimization problems with a possibly nonsmooth objective function. The key idea is to first specify a class of optimization algorithms using a generic iterative scheme involving only linear operations and applications of proximal operators. This scheme contains many modern primal-dual first-order solvers like the Douglas-Rachford and hybrid gradient methods as special cases. Moreover, we show convergence to an optimal point for a new method which also belongs to this class. Next, we interpret the generic scheme as a neural network and use unsupervised training to learn the best set of parameters for a specific class of objective functions while imposing a fixed number of iterations. In contrast to other approaches of "learning to optimize", we present an approach which learns parameters only in the set of convergent schemes. As use cases, we consider optimization problems arising in tomographic reconstruction and image deconvolution, and in particular a family of total variation regularization problems.