5 papers
A Distributionally Robust Framework for Learned Reconstructions in Inverse Problems
Floor van Maarschalkerwaart, Subhadip Mukherjee, Christoph Brune +1
Learned reconstruction operators for inverse problems are typically trained under a fixed noise model, and generalize poorly when the distribution during testing differs from the o…
Multi-Headed Transformer Architectures as Time-dependent Wasserstein Gradient Flows
Alex Massucco, Leonardo Del Grande, Marcello Carioni +2
In recent years, transformer architectures have revolutionized the field of language processing, opening the door to previously unforeseen possibilities. However, from a theoretica…
A Dual Certificate Approach to Sparsity in Infinite-Width Shallow Neural Networks
Leonardo Del Grande, Christoph Brune, Marcello Carioni
In this paper, we study total variation (TV)-regularized training of infinite-width shallow ReLU neural networks, formulated as a convex optimization problem over measures on the u…
An invertible generative model for forward and inverse problems
Tristan van Leeuwen, Christoph Brune, Marcello Carioni +1
We formulate inverse problems in a Bayesian framework and aim to train an invertible generative model that is capable of simulation (i.e., sampling from the likelihood) and inferen…
Perturbation-Aware Distributionally Robust Optimization for Inverse Problems
Floor van Maarschalkerwaart, Subhadip Mukherjee, Malena Sabaté Landman +2
This paper builds on classical distributionally robust optimization techniques to construct a comprehensive framework that can be used for solving inverse problems. Given an estima…