Fernsel, P;
Kereta, Ž;
Denker, A;
(2024)
Convergence Properties of Score-Based Models for Linear Inverse Problems Using Graduated Optimisation.
In:
Proceedings of the IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP) 2024.
(pp. pp. 1-6).
Institute of Electrical and Electronics Engineers (IEEE)
Preview |
Text
ConvergencePropertiesOfScoreBasedDiffusion.pdf - Accepted Version Download (3MB) | Preview |
Abstract
The incorporation of generative models as regularisers within variational formulations for inverse problems has proven effective across numerous image reconstruction tasks. However, the resulting optimisation problem is often non-convex and challenging to solve. In this work, we show that score-based generative models (SGMs) can be used in a graduated optimisation framework to solve inverse problems. We show that the resulting graduated non-convexity flow converge to stationary points of the original problem and provide a numerical convergence analysis of a 2D toy example. We further provide experiments on computed tomography image reconstruction, where we show that this framework is able to recover high-quality images, independent of the initial value. The experiments highlight the potential of using SGMs in graduated optimisation frameworks. The code is available11https://github.com/alexdenker/GradOpt-SGM.
| Type: | Proceedings paper |
|---|---|
| Title: | Convergence Properties of Score-Based Models for Linear Inverse Problems Using Graduated Optimisation |
| Event: | The 34th International Workshop on Machine Learning for Signal Processing (MLSP) 2024 |
| Location: | London, UK |
| Dates: | 22nd-25th September 2024 |
| ISBN-13: | 979-8-3503-7225-0 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/MLSP58920.2024.10734770 |
| Publisher version: | https://doi.org/10.1109/mlsp58920.2024.10734770 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10204139 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
