3 citations · 15 across the 36 of their papers we have counts for
5 papers · 1 filter
On the Inverse Flow Matching Problem in the One-Dimensional and Gaussian Cases
Alexander Korotin, Gudmund Pammer
This paper studies the inverse problem of flow matching (FM) between distributions with finite exponential moment, a problem motivated by modern generative AI applications such as…
Tighter Learning Guarantees on Digital Computers via Concentration of Measure on Finite Spaces
Anastasis Kratsios, A. Martina Neuman, Gudmund Pammer
Machine learning models with inputs in a Euclidean space , when implemented on digital computers, generalize, and their generalization gap converges to at a rate…
Estimating Barycenters of Distributions with Neural Optimal Transport
Alexander Kolesov, Petr Mokrov, Igor Udovichenko +4
Given a collection of probability measures, a practitioner sometimes needs to find an "average" distribution which adequately aggregates reference distributions. A theoretically ap…
Energy-Guided Continuous Entropic Barycenter Estimation for General Costs
Alexander Kolesov, Petr Mokrov, Igor Udovichenko +5
Optimal transport (OT) barycenters are a mathematically grounded way of averaging probability distributions while capturing their geometric properties. In short, the barycenter tas…
Designing Universal Causal Deep Learning Models: The Geometric (Hyper)Transformer
Beatrice Acciaio, Anastasis Kratsios, Gudmund Pammer
Several problems in stochastic analysis are defined through their geometry, and preserving that geometric structure is essential to generating meaningful predictions. Nevertheless,…