A Unified Kullback--Leibler Divergence Analysis of Generative Diffusion Models via Entropy Production Rate
Han Wu, Zhiwen Zhang
math.NA, stat.ML
Submitted: 2026-08-03
Comments: 37 pages, 15 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
- Time reversal of diffusion processes under a finite entropy condition
- Convergence of flow-based generative models via proximal gradient descent in Wasserstein space
- KL Convergence Guarantees for Score diffusion models under minimal data assumptions
- The entropy production of stationary diffusions
- Convergence Analysis for General Probability Flow ODEs of Diffusion Models in Wasserstein Distances
- Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models
- Estimates of the numerical density for stochastic differential equations with multiplicative noise
- Fast Diffusion Probabilistic Model Sampling through the lens of Backward Error Analysis
- Generative Diffusion From An Action Principle
- Neural Entropy
- Thermodynamics of the General Diffusion Process: Equilibrium Supercurrent and Nonequilibrium Driven Circulation with Dissipation
- The Effect of Stochasticity in Score-Based Diffusion Sampling: a KL Divergence Analysis
- Numerical approximation of effective diffusivities in homogenization of nondivergence-form equations with large drift by a Lagrangian method
- A structure-preserving scheme for computing effective diffusivity and anomalous diffusion phenomena of random 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
- 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