Neural Sampling with Reweighted Normalizing Flows via the Wasserstein--Fisher--Rao JKO Scheme

arXiv:2610.10278 · math.NA, cs.LG, cs.NA, math.PR, stat.ML · Submitted 2026-10-07 · Read on arXiv

math.NA, cs.LG, cs.NA, math.PR, stat.ML

Submitted: 2026-10-07

Updated: 2026-10-07

Terminology

• Gradient Flow — 15× in this paper · explained in 2 episodes
• Normalizing Flow — 11× in this paper · explained in 3 episodes
• Normalizing Flows — 8× in this paper · explained in 4 episodes
• Latent Space — 5× in this paper · explained in 7 episodes
• Optimal Transport — 5× in this paper · explained in 5 episodes
• Trace — 5× in this paper · explained in 2 episodes
• Inverse Problem — 4× in this paper · explained in 2 episodes
• Loss Function — 4× in this paper · explained in 2 episodes
• Degeneracy — 3× in this paper · explained in 3 episodes
• Hamiltonian Monte Carlo — 3× in this paper
• Bayesian Inference — 2× in this paper · explained in 5 episodes
• Uncertainty Quantification — 2× in this paper · explained in 8 episodes
• Admissibility — 1× in this paper · explained in 2 episodes
• Data Assimilation — 1× in this paper · explained in 2 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Flow Matching — 1× in this paper · explained in 8 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Kullback-Leibler (KL) Divergence — 1× in this paper · explained in 3 episodes
• Langevin Dynamics — 1× in this paper · explained in 2 episodes
• Metastability — 1× in this paper · explained in 2 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Theoretical Guarantees — 1× in this paper · explained in 2 episodes

Sources

• A Conceptual Introduction to Hamiltonian Monte Carlo
• Provable Diffusion Posterior Sampling for Bayesian Inversion
• Sequential Monte Carlo approximations of Wasserstein--Fisher--Rao gradient flows
• Accelerating Langevin Sampling with Birth-death
• Hellinger-Kantorovich Gradient Flows: Global Exponential Decay of Entropy Functionals
• Kernel Approximation of Fisher-Rao Gradient Flows

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
• Second-order consistency for learning chaotic dynamics via randomized Jacobian matching
• Windowed thinning and query complexity for the bouncy particle and Zigzag samplers
• Data-efficient Kernel Methods for Learning Hamiltonian Systems
• Adjoint Method versus Physics-Informed Neural Networks in PDE-Constrained Inverse Problems