# Local Linear Convergence of ISTA and FISTA on the LASSO Problem

arXiv: https://arxiv.org/abs/1501.02888 · HTML: https://mlsanity.com/paper/1501.02888/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2015.

## Built on by (most cited first, 8 of 8)

- [Stable and Interpretable Unrolled Dictionary Learning](https://mlsanity.com/paper/2106.00058/) (2021)
- [Fast and Robust Sparsity Learning over Networks: A Decentralized Surrogate Median Regression Approach](https://mlsanity.com/paper/2202.05498/) (2022)
- [Reverse engineering adversarial attacks with fingerprints from adversarial examples](https://mlsanity.com/paper/2301.13869/) (2023)
- [Diffusion Generative Models Meet Compressed Sensing, with Applications to Imaging and Finance](https://mlsanity.com/paper/2509.03898/) (2025)
- [Improved sparse PCA method for face and image recognition](https://mlsanity.com/paper/2112.00207/) (2021)
- [A statistical perspective on algorithm unrolling models for inverse problems](https://mlsanity.com/paper/2311.06395/) (2023)
- [Plug-and-Play Algorithm Convergence Analysis From The Standpoint of Stochastic Differential Equation](https://mlsanity.com/paper/2404.13866/) (2024)
- [Adaptive Iterative Soft-Thresholding Algorithm with the Median Absolute Deviation](https://mlsanity.com/paper/2507.02084/) (2025)

## Abstract (arXiv)

We establish local linear convergence bounds for the ISTA and FISTA iterations on the model LASSO problem. We show that FISTA can be viewed as an accelerated ISTA process. Using a spectral analysis, we show that, when close enough to the solution, both iterations converge linearly, but FISTA slows down compared to ISTA, making it advantageous to switch to ISTA toward the end of the iteration processs. We illustrate the results with some synthetic numerical examples.