Stochastic interpolants: a unifying framework for flows and diffusions

MaRDI QIDQ7308315zbMATH OpenFDO

Authors Michael S. Albergo, Nicholas M. Boffi, Eric Vanden-Eijnden

Publication date 4 August 2026

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://jmlr.org/papers/v26/23-1605.html

Mathematics Subject Classification ID

Diffusion processes (60J60) Density estimation (62G07) Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
• A Connection Between Score Matching and Denoising Autoencoders
• A Family of Nonparametric Density Estimation Algorithms
• A generalization of Caffarelli's contraction theorem via (reverse) heat flow
• A survey of the Schrödinger problem and some of its connections with optimal transport
• An Information-Theoretic View of Stochastic Localization
• Convergence of score-based generative modeling for general data distributions
• Density estimation by dual ascent of the log-likelihood
• Estimation of non-normalized statistical models by score matching
• Estimation of the mean of a multivariate normal distribution
• Exploratory Projection Pursuit
• Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
• scientific article; zbMATH DE number 3857407 (Why is no real title available?)
• scientific article; zbMATH DE number 3875656 (Why is no real title available?)
• scientific article; zbMATH DE number 3894218 (Why is no real title available?)
• Optimal Transport
• Polar factorization and monotone rearrangement of vector‐valued functions
• Reverse-time diffusion equation models
• Stochastic control liaisons. Richard Sinkhorn meets Gaspard Monge on a Schrödinger bridge
• Thin shell implies spectral gap up to polylog via a stochastic localization scheme

Cited in

(3)

• Stability of the Kim-Milman flow map
• Multimodal sampling via Schrödinger-Föllmer samplers with temperatures
• Mitigating mode collapse in normalizing flows by annealing with an adaptive schedule: application to parameter estimation

This page was built for publication: Stochastic interpolants: a unifying framework for flows and diffusions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7308315)