Geometry and Stochastic Analysis of Flow and Diffusion Models: A Survey
math.PR, math.DG, stat.ML
Submitted: 2026-11-09
Updated: 2026-11-09
License: http://creativecommons.org/licenses/by/4.0/
The gist: Flow-based and diffusion-based models have become the principal means of learning and sampling high-dimensional probability distributions, from images and video to proteins…
Terminology
Abstract
Flow-based and diffusion-based models have become the principal means of learning and sampling high-dimensional probability distributions, from images and video to proteins, molecules and physical fields, and increasingly language. Each carries a simple law to the law of the data along a curve of probability measures, and behind the variety of their names lie three geometries, those of the state space on which the data live, of the space of probability measures through which the curve passes, and of the space of paths traced by the generating process. A single analytic idea runs through the subject. Every score identity used to train a diffusion model is an integration by parts, on the noise, on the data or on Wiener space, and Malliavin calculus extends this to nonlinear and infinite-dimensional diffusions. We develop these foundations with full definitions and follow them through normalising flows, flow matching and few-step maps, diffusion models and their convergence theory, conditioning, Schrödinger bridges and stochastic control, and their extension to manifolds, Lie groups, discrete and function spaces and jump processes. We close with statistical physics, renormalisation and, more speculatively, holography, in which the radial direction of anti-de Sitter space can play the role of flow time. A table of the main methods and a collection of open problems complete the survey.
Sources
- Normalizing flows for lattice gauge theory in arbitrary space-time dimension
- Losing dimensions: Geometric memorization in generative diffusion
- On the Convergence and Straightness of Rectified Flow
- Minimax Optimality of the Probability Flow ODE for Diffusion Models
- Towards High-Order Mean Flow Generative Models: Feasibility, Expressivity, and Provably Efficient Criteria
- Generalization Properties of Score-matching Diffusion Models for Intrinsically Low-dimensional Data
- Tutorial on Diffusion Models for Imaging and Vision
- Inference-Time Alignment for Diffusion Models via Variationally Stable Doob's Matching
- An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization
- Sampling via Gradient Flows in the Space of Probability Measures
- Robustness and Structure Preservation in Flow-Based Generative Models via Wasserstein Path-Space Divergences
- KL Convergence Guarantees for Score diffusion models under minimal data assumptions
- Renormalizing Diffusion Models
- A Survey on Diffusion Models for Inverse Problems
- Generalised Flow Maps for Few-Step Generative Modelling on Riemannian Manifolds
- Augmented Bridge Matching
- Target Score Matching
- Scaling Up Machine Learning For Quantum Field Theory with Equivariant Continuous Flows
- Generative Modeling via Drifting
- NICE: Non-linear Independent Components Estimation
Related papers
- Rank-One HCIZ Integrals and Multiplicative Convolutions
- Repeated averaging on random d-regular graphs
- Precise cover times for branching random walks on Hamming graphs: (iterated) logarithmic corrections
- Markov Chain CLTs: Resolving Open Problems
- Marked stable L'evy processes in Brownian local time
- A Sharp Refinement of Samuels' Inequality via Cap Moves