• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Book chapter
  • Flow-Matching Sampling in Physics-Informed Neural Networks for PDEs with Sharp Source Terms
  • RU
  • EN
Расширенный поиск
Высшая школа экономики
Национальный исследовательский университет
Priority areas
  • business informatics
  • economics
  • engineering science
  • humanitarian
  • IT and mathematics
  • law
  • management
  • mathematics
  • sociology
  • state and public administration
by year
  • 2028
  • 2027
  • 2026
  • 2025
  • 2024
  • 2023
  • 2022
  • 2021
  • 2020
  • 2019
  • 2018
  • 2017
  • 2016
  • 2015
  • 2014
  • 2013
  • 2012
  • 2011
  • 2010
  • 2009
  • 2008
  • 2007
  • 2006
  • 2005
  • 2004
  • 2003
  • 2002
  • 2001
  • 2000
  • 1999
  • 1998
  • 1997
  • 1996
  • 1995
  • 1994
  • 1993
  • 1992
  • 1991
  • 1990
  • 1989
  • 1988
  • 1987
  • 1986
  • 1985
  • 1984
  • 1983
  • 1982
  • 1981
  • 1980
  • 1979
  • 1978
  • 1977
  • 1976
  • 1975
  • 1974
  • 1973
  • 1972
  • 1971
  • 1970
  • 1969
  • 1968
  • 1967
  • 1966
  • 1965
  • 1964
  • 1963
  • 1958
  • More
Subject
News
August 25, 2026
Scientists Develop Algorithm for More Reliable Processors in Data Centres
Researchers from HSE MIEM and Samara University have developed the LRF-3D algorithm to automatically bypass idle nodes in three-dimensional networks-on-chip. Thanks to its hierarchical architecture, the algorithm outperforms existing solutions in both speed and path accuracy, improving processor reliability for use in data centres, supercomputers, and AI computing. The source code and test results are publicly available.
August 24, 2026
Researchers Develop Method for Direct Generation of Regulatory DNA
Researchers at HSE University have developed a model for generating promoters and enhancers—DNA sequences that regulate gene activity. The model works directly with DNA nucleotides, without first transforming them into a continuous numerical representation. This solution could be useful for applications in synthetic biology and gene therapy. The study results were presented at the ICLR 2026 Workshop ‘Generative AI in Genomics (Gen^2): Barriers and Frontiers.’
August 21, 2026
Social Integration: At the Crossroads of Knowledge and Values
The International Laboratory for Social Integration Research (ILSIR) at HSE University studies the challenges faced by vulnerable groups and explores ways to help them participate fully in everyday life. To develop effective solutions, the laboratory’s researchers combine cutting-edge methods with practical fieldwork. In this interview with the HSE News Service, Laboratory Head Elena Iarskaia-Smirnova discusses the laboratory’s work.

 

Have you spotted a typo?
Highlight it, click Ctrl+Enter and send us a message. Thank you for your help!

Publications
  • Books
  • Articles
  • Chapters of books
  • Working papers
  • Report a publication
  • Research at HSE

?

Flow-Matching Sampling in Physics-Informed Neural Networks for PDEs with Sharp Source Terms

.
Khassan Y., Efremenko D., Buzaev F., Derkach D.

Singularities in the source functions of partial differential equations (PDEs) pose significant challenges for physics-informed neural networks (PINNs), often leading to numerical instability and requiring a large number of sampling points to achieve accurate solutions, which increases computational costs. In this paper, we propose a novel sampling strategy that uses diffusion models for generative sampling based on the distribution of PDE residuals. Using the optimal transport coupling flow-matching technique, our method adaptively generates additional sampling points in regions with high residuals, enhancing both solution accuracy and efficiency. Unlike existing approaches, which explicitly model probability densities proportional to residuals, our technique uses flow matching to directly sample from complex residual distributions, improving PINN performance for problems with sharply localized source terms. We validate our method on the Poisson equation with singular source functions and the linear elasticity equation in materials with complex geometries, achieving up to 10x lower MSE compared to baseline methods and outperforming normalizing flow-based sampling.

Language: English
Keywords: Physics Informed Neural Networks

In book

AI & PDE: ICLR 2026 Workshop on AI and Partial Differential Equations
[б.и.], 2026.
Similar publications
Relative Position Biases for Transformer PINNs
Buzaev F., Andrei Ermakov, Ivanova M. et al., , in: AI & PDE: ICLR 2026 Workshop on AI and Partial Differential Equations.: [б.и.], 2026.
Transformer-based physics-informed neural networks (PINNs) have recently improved PDE solving by modeling spatiotemporal interactions with self-attention, yet most variants still rely on absolute coordinate embeddings. We ask whether relative positional structure - a key inductive bias in modern Transformers can be made coordinate-aware and yield an accuracy boost with minimal overhead for PDE PINNs. Building ...
Added: June 24, 2026
Physics-Constrained Neural Networks for Improved Short-Term Weather Forecasting: A Case Study over the South Pacific
Bugaev E., Buzaev F., Efremenko D. et al., , in: AI & PDE: ICLR 2026 Workshop on AI and Partial Differential Equations.: [б.и.], 2026.
This study introduces enhancements to physics-constrained neural networks (PCNNs) that improve the accuracy and stability of hybrid short-term weather forecasting models. Building on the WeatherGFT architecture, three innovations are proposed. First, an upgraded numerical solver, combining a fifth-order weighted essentially non-oscillatory scheme (WENO-5), a beta-plane approximation, and subgrid-scale viscosity, permits a fourfold increase in the ...
Added: June 24, 2026
Solution of the Multimode Nonlinear Schrödinger Equation Using Physics-Informed Neural Networks
Buzaev F., Чупров И. А., Efremenko D. et al., Doklady Mathematics 2025
Single-mode optical fibers (SMFs) have become the foundation of modern communication systems. However, their capacity is expected to reach its theoretical limit in the near future. The use of multimode fibers (MMF) is seen as one of the most promising solutions to address this capacity deficit. The multimode nonlinear Schrödinger equation (MMNLSE) describing light propagation ...
Added: April 28, 2025
Search for Optimal Architecture of Physics-Informed Neural Networks Using Differential Evolution Algorithm
F. A. Buzaev, D. S. Efremenko, I. A. Chuprov et al., Doklady Mathematics 2025 Vol. 110 P. S8–S14
The accuracy of solving partial differential equations using physics-informed neural networks (PINNs) significantly depends on their architecture and the choice of hyperparameters. However, manually searching for the optimal configuration can be difficult due to the high computational complexity. In this paper, we propose an approach for optimizing the PINN architecture using a differential evolution algorithm. ...
Added: April 28, 2025
Optimization of Physics-Informed Neural Networks for Solving the Nolinear Schrödinger Equation
Buzaev F., Чупров И. А., Efremenko D., Doklady Mathematics 2023 Vol. 108 No. S2 P. S186–S195
Physics Informed Neural Networks (PINN) is a promising method for solving partial differential equations using machine learning. In this paper we consider the application of PINN to the nonlinear Schrödinger equation to describe the propagation of signal in an optical fibre. The factors determining the convergence of PINN from the physical point of view are ...
Added: April 3, 2024
Оптимизация физико-информированных нейронных сетей для решения нелинейного уравнения Шредингера
Чупров И. А., Гао Ц., Efremenko D. et al., Доклады Российской академии наук. Математика, информатика, процессы управления (ранее - Доклады Академии Наук. Математика) 2023 Т. 514 № 2 С. 28–38
Физико-информированные нейронные сети (Physics Informed Neural Networks – PINN) являются перспективным методом решения уравнений в частных производных с помощью машинного обучения. В работе рассмотрено применение PINN к нелинейному уравнению Шредингера для описания ...
Added: December 19, 2023
Hybrid acceleration techniques for the physics-informed neural networks: a comparative analysis
Buzaev F., Gao J., Ivan Chuprov et al., Machine Learning 2024 Vol. 113 No. 6 P. 3675 –3692
Physics-informed neural networks (PINN) has emerged as a promising approach for solving partial differential equations (PDEs). However, the training process for PINN can be computationally expensive, limiting its practical applications. To address this issue, we investigate several acceleration techniques for PINN that combine Fourier neural operators, separable PINN, and first-order PINN. We also propose novel ...
Added: December 19, 2023
  • About
  • About
  • Key Figures & Facts
  • Sustainability at HSE University
  • Faculties & Departments
  • International Partnerships
  • Faculty & Staff
  • HSE Buildings
  • HSE University for Persons with Disabilities
  • Public Enquiries
  • Studies
  • Admissions
  • Programme Catalogue
  • Undergraduate
  • Graduate
  • Exchange Programmes
  • Summer University
  • Summer Schools
  • Semester in Moscow
  • Business Internship
  • Research
  • International Laboratories
  • Research Centres
  • Research Projects
  • Monitoring Studies
  • Conferences & Seminars
  • Academic Jobs
  • Yasin (April) International Academic Conference on Economic and Social Development
  • Media & Resources
  • Publications by staff
  • HSE Journals
  • Publishing House
  • iq.hse.ru: commentary by HSE experts
  • Library
  • Economic & Social Data Archive
  • Video
  • HSE Repository of Socio-Economic Information
  • HSE1993–2026
  • Contacts
  • Copyright
  • Privacy Policy
  • Site Map
Edit