collaborators

6 papers

stat.ML2026

Statistical inverse learning and -regularization

Abhishake Rastogi, Tatiana A. Bubba, Tapio Helin +1

We study the recovery of sparse functions from finite, noisy, and indirect observations in the framework of statistical inverse learning. The unknown is modeled as an element of $\…

math.NA2026

A Line--Search--Based Stochastic Gradient Method for 3D Computed Tomography

Tatiana A. Bubba, Elena Morotti, Federica Porta +2

We introduce FB-LISA, a forward-backward (FB) generalization of a recently proposed line-search-based stochastic gradient algorithm to address the imaging problem of volumetric rec…

math.NA2025

Regularization with optimal space-time priors

Tatiana A. Bubba, Tommi Heikkilä, Demetrio Labate +1

We propose a variational regularization approach based on a multiscale representation called cylindrical shearlets aimed at dynamic imaging problems, especially dynamic tomography.…

math.OC2025

Fast Inexact Bilevel Optimization for Analytical Deep Image Priors

Mohammad Sadegh Salehi, Tatiana A. Bubba, Yury Korolev

The analytical deep image prior (ADP) introduced by Dittmer et al. (2020) establishes a link between deep image priors and classical regularization theory via bilevel optimization.…

eess.IV2025

TomoSelfDEQ: Self-Supervised Deep Equilibrium Learning for Sparse-Angle CT Reconstruction

Tatiana A. Bubba, Matteo Santacesaria, Andrea Sebastiani

Deep learning has emerged as a powerful tool for solving inverse problems in imaging, including computed tomography (CT). However, most approaches require paired training data with…

math.OC2025

Revisiting DONet: microlocally inspired filters for incomplete-data tomographic reconstructions

Tatiana A. Bubba, Luca Ratti, Andrea Sebastiani

In this paper, we revisit a supervised learning approach based on unrolling, known as DONet, by providing a deeper microlocal interpretation for its theoretical analysis, and e…