A kernel method for the learning of Wasserstein geometric flows
math.NA, cs.NA, math.DS, math.ST, stat.TH
Submitted: 2025-11-10
Updated: 2026-11-17
Code: https://github.com/jianyuhu/kernel-learning-for-Wasserstein-flows
Terminology
Sources
- Self-test loss functions for learning weak-form operators and gradient flows
- Transport information geometry I: Riemannian calculus on probability simplex
- Learning Generalized Diffusions using an Energetic Variational Approach
Related papers
- Do physics-informed neural networks (PINNs) need to be deep? Shallow PINNs using the Levenberg-Marquardt algorithm
- A Neural-preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
- Advanced Linear Algebra with Applications - Part I (Numerical linear algebra for PDEs, machine learning, and data assimilation)
- Operator learning meets inverse problems: A probabilistic perspective
- Second-order consistency for learning chaotic dynamics via randomized Jacobian matching
- Windowed thinning and query complexity for the bouncy particle and Zigzag samplers