The monge gap: A regularizer to learn all transport maps
Optimal transport (OT) theory has been used in machine learning to study and characterize
maps that can push-forward efficiently a probability measure onto another. Recent works …
maps that can push-forward efficiently a probability measure onto another. Recent works …
Extremal domain translation with neural optimal transport
M Gazdieva, A Korotin… - Advances in Neural …, 2024 - proceedings.neurips.cc
In many unpaired image domain translation problems, eg, style transfer or super-resolution,
it is important to keep the translated image similar to its respective input image. We propose …
it is important to keep the translated image similar to its respective input image. We propose …
Generative Entropic Neural Optimal Transport To Map Within and Across Spaces
Learning measure-to-measure mappings is a crucial task in machine learning, featured
prominently in generative modeling. Recent years have witnessed a surge of techniques …
prominently in generative modeling. Recent years have witnessed a surge of techniques …
Modelling single-cell RNA-seq trajectories on a flat statistical manifold
Optimal transport has demonstrated remarkable potential in the field of single-cell biology,
addressing relevant tasks such as trajectory modelling and perturbation effect prediction …
addressing relevant tasks such as trajectory modelling and perturbation effect prediction …