Mean-field and kinetic descriptions of neural differential equations
From MaRDI portal
Publication:2148968
DOI10.3934/fods.2022007zbMath1489.35280arXiv2001.04294OpenAlexW3211861249WikidataQ115219039 ScholiaQ115219039MaRDI QIDQ2148968
Torsten Trimborn, Giuseppe Visconti, Michael Herty
Publication date: 24 June 2022
Published in: Foundations of Data Science (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2001.04294
Sensitivity, stability, parametric optimization (90C31) Neural networks for/in biological studies, artificial life and related topics (92B20) Vlasov equations (35Q83) Fokker-Planck equations (35Q84)
Related Items
Reproducing kernel Hilbert spaces in the mean field limit, Continuous limits of residual neural networks in case of large input data
Uses Software
Cites Work
- Self-similarity and power-like tails in nonconservative kinetic models
- Kinetic models of opinion formation
- Large scale dynamics of the persistent turning Walker model of fish behavior
- Stability and total variation estimates on general scalar balance laws
- Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
- Efficient implementation of weighted ENO schemes
- Deep neural networks motivated by partial differential equations
- Optimal transport natural gradient for statistical manifolds with continuous sample space
- Wasserstein proximal of GANs
- Non-intrusive reduced order modeling of unsteady flows using artificial neural networks with application to a combustion problem
- Detecting troubled-cells on two-dimensional unstructured grids using a neural network
- Kinetic modeling of alcohol consumption
- Mean field analysis of neural networks: a central limit theorem
- A machine learning framework for data driven acceleration of computations of differential equations
- Kinetic methods for inverse problems
- A review of the mean field limits for Vlasov equations
- An artificial neural network as a troubled-cell indicator
- A short discussion is followed by an agreement on the global minimum: consensus-based global optimization
- A Third-Order Semidiscrete Central Scheme for Conservation Laws and Convection-Diffusion Equations
- Machine learning: Trends, perspectives, and prospects
- Particle, kinetic, and hydrodynamic models of swarming
- Convergence of a first-order consensus-based global optimization algorithm
- Compact Central WENO Schemes for Multidimensional Conservation Laws
- CWENO: Uniformly accurate reconstructions for balance laws
- GENERALIZED KINETIC (BOLTZMANN) MODELS: MATHEMATICAL STRUCTURES AND APPLICATIONS
- Complex Systems and Society
- A mean field view of the landscape of two-layer neural networks
- Machine Learning and Artificial Intelligence
- Ensemble Kalman inversion: a derivative-free technique for machine learning tasks
- Learning in Modal Space: Solving Time-Dependent Stochastic PDEs Using Physics-Informed Neural Networks
