Smart Flow Matching: On The Theory of Flow Matching Algorithms with Applications

no code implementations • 5 Feb 2024 • Gleb Ryzhakov, Svetlana Pavlova, Egor Sevriugov, Ivan Oseledets

The paper presents the exact formula for the vector field that minimizes the loss for the standard flow.

Black-Box Approximation and Optimization with Hierarchical Tucker Decomposition

no code implementations • 5 Feb 2024 • Gleb Ryzhakov, Andrei Chertkov, Artem Basharin, Ivan Oseledets

We develop a new method HTBB for the multidimensional black-box approximation and gradient-free optimization, which is based on the low-rank hierarchical Tucker decomposition with the use of the MaxVol indices selection procedure.

Understanding DDPM Latent Codes Through Optimal Transport

no code implementations • 14 Feb 2022 • Valentin Khrulkov, Gleb Ryzhakov, Andrei Chertkov, Ivan Oseledets

Diffusion models have recently outperformed alternative approaches to model the distribution of natural images, such as GANs.

Two-phase approaches to optimal model-based design of experiments: how many experiments and which ones?

no code implementations • 22 Jan 2021 • Charlie Vanaret, Philipp Seufert, Jan Schwientek, Gleb Karpov, Gleb Ryzhakov, Ivan Oseledets, Norbert Asprion, Michael Bortz

Model-based experimental design is attracting increasing attention in chemical process engineering.

Optimization and Control