Alert button
Picture for Nikita Gushchin

Nikita Gushchin

Alert button

Light Schrödinger Bridge

Oct 02, 2023
Alexander Korotin, Nikita Gushchin, Evgeny Burnaev

Despite the recent advances in the field of computational Schrodinger 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 plays the role of simple-yet-effective baseline for SB just like, e.g., $k$-means method in clustering, logistic regression in classification or Sinkhorn algorithm in discrete optimal transport. We address this issue and propose a novel fast and simple SB solver. Our development is a smart combination of two ideas which recently appeared in the field: (a) parameterization of the Schrodinger potentials with sum-exp quadratic functions and (b) viewing the log-Schrodinger potentials as the energy functions. We show that combined together these ideas yield a lightweight, simulation-free and theoretically justified SB solver with a simple straightforward optimization objective. As a result, it allows solving SB in moderate dimensions in a matter of minutes on CPU without a painful hyperparameter selection. Our light solver resembles the Gaussian mixture model which is widely used for density estimation. Inspired by this similarity, we also prove an important theoretical result showing that our light solver is a universal approximator of SBs. The code for the LightSB solver can be found at https://github.com/ngushchin/LightSB

Viaarxiv icon

Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark

Jun 16, 2023
Nikita Gushchin, Alexander Kolesov, Petr Mokrov, Polina Karpikova, Andrey Spiridonov, Evgeny Burnaev, Alexander Korotin

Figure 1 for Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark
Figure 2 for Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark
Figure 3 for Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark
Figure 4 for Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark

Over the last several years, there has been a significant progress in developing neural solvers for the Schr\"odinger Bridge (SB) problem and applying them to generative modeling. This new research field is justifiably fruitful as it is interconnected with the practically well-performing diffusion models and theoretically-grounded entropic optimal transport (EOT). Still the area lacks non-trivial tests allowing a researcher to understand how well do the methods solve SB or its equivalent continuous EOT problem. We fill this gap and propose a novel way to create pairs of probability distributions for which the ground truth OT solution in known by the construction. Our methodology is generic and works for a wide range of OT formulations, in particular, it covers the EOT which is equivalent to SB (the main interest of our study). This development allows us to create continuous benchmark distributions with the known EOT and SB solution on high-dimensional spaces such as spaces of images. As an illustration, we use these benchmark pairs to test how well do existing neural EOT/SB solvers actually compute the EOT solution. The benchmark is available via the link: https://github.com/ngushchin/EntropicOTBenchmark.

Viaarxiv icon

Entropic Neural Optimal Transport via Diffusion Processes

Nov 02, 2022
Nikita Gushchin, Alexander Kolesov, Alexander Korotin, Dmitry Vetrov, Evgeny Burnaev

Figure 1 for Entropic Neural Optimal Transport via Diffusion Processes
Figure 2 for Entropic Neural Optimal Transport via Diffusion Processes
Figure 3 for Entropic Neural Optimal Transport via Diffusion Processes
Figure 4 for Entropic Neural Optimal Transport via Diffusion Processes

We propose a novel neural algorithm for the fundamental problem of computing the entropic optimal transport (EOT) plan between probability distributions which are accessible by samples. Our algorithm is based on the saddle point reformulation of the dynamic version of EOT which is known as the Schr\"odinger Bridge problem. In contrast to the prior methods for large-scale EOT, our algorithm is end-to-end and consists of a single learning step, has fast inference procedure, and allows handling small values of the entropy regularization coefficient which is of particular importance in some applied problems. Empirically, we show the performance of the method on several large-scale EOT tasks.

Viaarxiv icon