Alexander Korotin
Alexander Korotin
Home
Publications
Team
CV
Light
Dark
Automatic
paper-conference
Categorical Schrodinger Bridge Matching
The paper develops a theoretical and algorithmic foundation for solving the Schrödinger Bridge problem in discrete spaces using Iterative Markovian Fitting, introducing the CSBM algorithm and validating it with experiments on synthetic data and vector-quantized images.
Grigory Ksenofontov
,
Alexander Korotin
PDF
Cite
OpenReview
Field Matching: an Electrostatic Paradigm to Generate and Transfer Data
We propose Electrostatic Field Matching (EFM), a novel method inspired by the physics of capacitors, which uses a neural network to learn electrostatic fields for generative modeling and distribution transfer.
Alexander Kolesov
,
Manukhov Stepan
,
Vladimir Palyulin
,
Alexander Korotin
PDF
Cite
OpenReview
Inverse Bridge Matching Distillation
We introduce a novel distillation technique for diffusion bridge models (DBMs) that significantly accelerates inference (4x to 100x) and improves generation quality by leveraging inverse bridge matching.
Nikita Gushchin
,
David Li
,
Daniil Selikhanovych
,
Evgeny Burnaev
,
Dmitry Baranchuk
,
Alexander Korotin
PDF
Cite
OpenReview
Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport
We propose a novel algorithm for learning barycentres of distributions using neural networks. The algorithm is scalable and robust to outliers.
Milena Gazdieva
,
Jaemoo Choi
,
Alexander Kolesov
,
Jaewoong Choi
,
Alexander Korotin
PDF
Cite
Code
Poster
Video
OpenReview
Energy-Guided Continuous Entropic Barycenter Estimation for General Costs
We propose a new energy-based method to compute entropic optimal transport barycenters with general cost functions.
Alexander Kolesov
,
Petr Mokrov
,
Igor Udovichenko
,
Milena Gazdieva
,
Gudmund Pammer
,
Anastasis Kratsios
,
Evgeny Burnaev
,
Alexander Korotin
PDF
Cite
Code
Video
OpenReview
Light Unbalanced Optimal Transport
We propose a novel theoretically-justified and lightweight solver for continuous unbalanced entropic optimal transport.
Milena Gazdieva
,
Arip Asadulaev
,
Evgeny Burnaev
,
Alexander Korotin
PDF
Cite
Code
Poster
Video
OpenReview
Estimating Barycenters of Distributions with Neural Optimal Transport
We propose a novel bi-level optimization algorithm for solving the continuous Wasserstein Barycenter problem based on Neural Optimal Transport.
Alexander Kolesov
,
Petr Mokrov
,
Igor Udovichenko
,
Milena Gazdieva
,
Gudmund Pammer
,
Evgeny Burnaev
,
Alexander Korotin
PDF
Cite
Code
Video
OpenReview
Light and Optimal Schrodinger Bridge Matching
We address propose a novel procedure to learn SB which exploits the optimal parameterization of the diffusion process and provably recovers the SB process (a) with a single bridge matching step and (b) with arbitrary transport plan as the input.
Nikita Gushchin
,
Sergey Kholkin
,
Evgeny Burnaev
,
Alexander Korotin
PDF
Cite
Code
Poster
Video
OpenReview
Rethinking Optimal Transport in Offline Reinforcement Learning
We propose a novel algorithm for offline reinforcement learning using optimal transport.
Arip Asadulaev
,
Rostislav Korst
,
Alexander Korotin
,
Vage Egiazarian
,
Andrey Filchenkov
,
Evgeny Burnaev
Cite
Code
Video
OpenReview
Adversarial Schrödinger Bridge Matching
We propose a novel iterative procedure with fast inference to learn the Schrodinger Bridge using the adversarial bridge matching in discrete time.
Nikita Gushchin
,
Daniil Selikhanovych
,
Sergey Kholkin
,
Evgeny Burnaev
,
Alexander Korotin
PDF
Cite
Code
Poster
Video
OpenReview
»
Cite
×