Sparsity Promoting Optimal Transport regularization for superresolution and data-driven models
Organization:
Funded by: | UT/EWI |
PhD: | |
Supervisor: Daily supervisor: | |
Collaboration: | - |
Description:
In this project, we plan to study the properties of solutions of sparsity-promoting models. In particular, we will focus on static and dynamic models regularized with Optimal Transport energies, with the goal of understanding the superresolution properties of Inverse Problems in the presence of noise. We will then apply the developed theory to analyze the dynamics and improve the training of Machine Learning models.
Output:
Publications:
2024
Exact sparse representation recovery in signal demixing and group BLASSO (2024)Proceedings in Applied Mathematics and Mechanics. Carioni, M. & Grande, L. D.https://doi.org/10.1002/pamm.202400156Exact Sparse Representation Recovery in Signal Demixing and Group BLASSO (2024)[Working paper › Preprint]. Carioni, M. & Grande, L. D.https://doi.org/10.48550/arXiv.2406.09922
2023
A General Theory for Exact Sparse Representation Recovery in Convex Optimization (2023)[Working paper › Preprint]. ArXiv.org. Carioni, M. & Grande, L. D.https://doi.org/10.48550/arXiv.2311.08072