Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Gushchin, Nikita"'
Autor:
Kholkin, Sergei, Ksenofontov, Grigoriy, Li, David, Kornilov, Nikita, Gushchin, Nikita, Burnaev, Evgeny, Korotin, Alexander
The Iterative Markovian Fitting (IMF) procedure based on iterative reciprocal and Markovian projections has recently been proposed as a powerful method for solving the Schr\"odinger Bridge problem. However, it has been observed that for the practical
Externí odkaz:
http://arxiv.org/abs/2410.02601
Autor:
Gushchin, Nikita, Selikhanovych, Daniil, Kholkin, Sergei, Burnaev, Evgeny, Korotin, Alexander
The Schr\"odinger Bridge (SB) problem offers a powerful framework for combining optimal transport and diffusion models. A promising recent approach to solve the SB problem is the Iterative Markovian Fitting (IMF) procedure, which alternates between M
Externí odkaz:
http://arxiv.org/abs/2405.14449
Schr\"odinger Bridges (SB) have recently gained the attention of the ML community as a promising extension of classic diffusion models which is also interconnected to the Entropic Optimal Transport (EOT). Recent solvers for SB exploit the pervasive b
Externí odkaz:
http://arxiv.org/abs/2402.03207
Despite the recent advances in the field of computational Schr\"odinger Bridges (SB), most existing SB solvers are still heavy-weighted and require complex optimization of several neural networks. It turns out that there is no principal solver which
Externí odkaz:
http://arxiv.org/abs/2310.01174
Autor:
Gushchin, Nikita, Kolesov, Alexander, Mokrov, Petr, Karpikova, Polina, Spiridonov, Andrey, Burnaev, Evgeny, Korotin, Alexander
Over the last several years, there has been significant progress in developing neural solvers for the Schr\"odinger Bridge (SB) problem and applying them to generative modelling. This new research field is justifiably fruitful as it is interconnected
Externí odkaz:
http://arxiv.org/abs/2306.10161
Energy-based models (EBMs) are known in the Machine Learning community for decades. Since the seminal works devoted to EBMs dating back to the noughties, there have been a lot of efficient methods which solve the generative modelling problem by means
Externí odkaz:
http://arxiv.org/abs/2304.06094
We propose a novel neural algorithm for the fundamental problem of computing the entropic optimal transport (EOT) plan between continuous probability distributions which are accessible by samples. Our algorithm is based on the saddle point reformulat
Externí odkaz:
http://arxiv.org/abs/2211.01156