3 papers
cs.LG2026
Riemannian Neural Hamiltonian Flows: Geodesic Symplectic Transport and Interpretability
Vincent Souveton
Hamiltonian normalizing flows are attractive generative models because their phase-space maps are invertible and volume preserving, but most neural constructions are formulated in…
cs.LG2025
Hamiltonian Normalizing Flows as kinetic PDE solvers: application to the 1D Vlasov-Poisson Equations
Vincent Souveton, Sébastien Terrana
Many conservative physical systems can be described using the Hamiltonian formalism. A notable example is the Vlasov-Poisson equations, a set of partial differential equations that…
cs.LG2023
Fixed-kinetic Neural Hamiltonian Flows for enhanced interpretability and reduced complexity
Vincent Souveton, Arnaud Guillin, Jens Jasche +2
Normalizing Flows (NF) are Generative models which transform a simple prior distribution into the desired target. They however require the design of an invertible mapping whose Jac…