Gabriele Steidl

Sparse ANOVA Inspired Mixture Models

2021 · arXiv (Cornell University)

Based on the analysis of variance (ANOVA) decomposition of functions which relies on the assumption that the function we wish to approximate can be well explained by limited variable interaction, we propose a sparse Gaussian-like …

Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching

2024 · arXiv (Cornell University)

In inverse problems, many conditional generative models approximate the posterior measure by minimizing a distance between the joint measure and its learned approximation. While this approach also controls the distance between the posterior measures in …