arXiv Machine Learning
Infinite-dimensional generative diffusions via Doob's h-transform
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Aug 5
Simulation-free and finite-time diffusion model
arXiv:2608. 03117v1 Announce Type: new Abstract: The performance of generative diffusion models is determined by the choice of the reference diffusion process connecting the empirical and prior distributions.
arXiv AI
Aug 5
A Hyperfinite Framework for Score-Based Generative Modeling
arXiv:2608. 02799v1 Announce Type: cross Abstract: Score-based diffusion models are typically formulated using continuous-time stochastic differential equations and measure-theoretic stochastic calculus.
arXiv Statistics ML
3d ago
Steepest Guidance: A Practical and Principled Approach to Inference-Time Alignment of Flow and Diffusion-based Models
arXiv:2609.39091v1 Announce Type: new Abstract: Inference-time alignment of flow and diffusion-based models is critical for achieving flexible generative modeling. Theoretically, Doob's $h$-transform...
arXiv Machine Learning
Jun 16
Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees
arXiv:2606. 16610v1 Announce Type: cross Abstract: Diffusion Flow Matching (DFM) has recently emerged as a versatile framework for generative modeling, yet its theoretical convergence properties remain only partially understood.
arXiv Machine Learning
Jun 4
On Forgetting and Stability of Score-based Generative models
arXiv:2601. 21868v2 Announce Type: replace-cross Abstract: Understanding the stability and long-time behavior of generative models is a fundamental problem in modern machine learning.
arXiv Machine Learning
Jun 30
The Fundamental Limits of Valid Transport Map Estimation
arXiv:2606. 30574v1 Announce Type: new Abstract: Many modern generative modeling methods, including diffusion models, normalizing flows, and flow matching, estimate transport maps or plans between distributions without explicitly targeting an optimal transport (OT) map.