English
Related papers

Related papers: On the Mathematics of Diffusion Models

200 papers

In this article we study the existence and uniqueness of strong solutions of a class of parameterized family of SDEs driven by L\'evy noise. These SDEs occurs in connection with a class of stochastic PDEs, which take values in the space of…

Probability · Mathematics 2018-01-23 Suprio Bhar , Barun Sarkar

Variational autoencoders (VAE) often use Gaussian or category distribution to model the inference process. This puts a limit on variational learning because this simplified assumption does not match the true posterior distribution, which is…

Machine Learning · Computer Science 2017-02-28 Ke Sun , Xiangliang Zhang

Stochastic differential equations (SDEs) are increasingly used in longitudinal data analysis, compartmental models, growth modelling, and other applications in a number of disciplines. Parameter estimation, however, currently requires…

Methodology · Statistics 2018-09-12 Oscar García

Score-based diffusion models generate samples from an unknown target distribution using a time-reversed diffusion process. While such models represent state-of-the-art approaches in industrial applications such as artificial image…

Machine Learning · Computer Science 2026-02-09 Adrian Baule

A common task in experimental sciences is to fit mathematical models to real-world measurements to improve understanding of natural phenomenon (reverse-engineering or inverse modeling). When complex dynamical systems are considered, such as…

Numerical Analysis · Mathematics 2018-06-18 Jean-Charles Croix , Nicolas Durrande , Mauricio Alvarez

A delayed term in a differential equation reflects the fact that information takes significant time to travel from one place to another within a process being studied. Despite de apparent similarity with ordinary differential equations,…

Dynamical Systems · Mathematics 2023-08-24 Gregory Kozyreff

Discrete diffusion models (DDMs) are a powerful class of generative models for categorical data, but they typically require many function evaluations for a single sample, making inference expensive. Existing acceleration methods either rely…

Machine Learning · Computer Science 2025-12-16 Yansong Gao , Yu Sun

We provide new convergence guarantees in Wasserstein distance for diffusion-based generative models, covering both stochastic (DDPM-like) and deterministic (DDIM-like) sampling methods. We introduce a simple framework to analyze…

Machine Learning · Computer Science 2025-11-14 Eliot Beyler , Francis Bach

We consider the problem of approximation of the solution of the backward stochastic differential equation in the Markovian case. We suppose that the trend coefficient of the diffusion process depends on some unknown parameter and the…

Statistics Theory · Mathematics 2013-05-17 Yury A. Kutoyants , Li Zhou

Many naturally-occuring models in the sciences are well-approximated by simplified models, using multiscale techniques. In such settings it is natural to ask about the relationship between inverse problems defined by the original problem…

Numerical Analysis · Mathematics 2019-02-28 Kit Newton , Qin Li , Andrew Stuart

In this article we study (possibly degenerate) stochastic differential equations (SDE) with irregular (or discontiuous) coefficients, and prove that under certain conditions on the coefficients, there exists a unique almost everywhere…

Probability · Mathematics 2009-08-18 Xicheng Zhang

Normalizing flows are a powerful class of generative models for continuous random variables, showing both strong model flexibility and the potential for non-autoregressive generation. These benefits are also desired when modeling discrete…

Machine Learning · Statistics 2019-06-06 Zachary M. Ziegler , Alexander M. Rush

Diffusion models (DMs) have proven to be effective in modeling high-dimensional distributions, leading to their widespread adoption for representing complex priors in Bayesian inverse problems (BIPs). However, current DM-based posterior…

Machine Learning · Computer Science 2025-06-06 Haoxuan Chen , Yinuo Ren , Martin Renqiang Min , Lexing Ying , Zachary Izzo

Variational autoencoders (VAEs) are a popular class of deep generative models with many variants and a wide range of applications. Improvements upon the standard VAE mostly focus on the modelling of the posterior distribution over the…

Machine Learning · Computer Science 2022-11-02 James Langley , Miguel Monteiro , Charles Jones , Nick Pawlowski , Ben Glocker

Often the regression function appearing in fields like economics, engineering, biomedical sciences obeys a system of higher order ordinary differential equations (ODEs). The equations are usually not analytically solvable. We are interested…

Statistics Theory · Mathematics 2015-05-19 Prithwish Bhaumik , Subhashis Ghosal

The connection between forward backward doubly stochastic differential equations and the optimal filtering problem is established without using the Zakai's equation. The solutions of forward backward doubly stochastic differential equations…

Numerical Analysis · Mathematics 2018-05-29 Richard Archibald , Feng Bao , Peter Maksymovych

Simulating parameter-dependent stochastic differential equations (SDEs) presents significant computational challenges, as separate high-fidelity simulations are typically required for each parameter value of interest. Despite the success of…

Machine Learning · Statistics 2026-02-03 Minglei Yang , Sicheng He

Stochastic differential equations (SDEs) are a ubiquitous modeling framework that finds applications in physics, biology, engineering, social science, and finance. Due to the availability of large-scale data sets, there is growing interest…

Machine Learning · Statistics 2025-03-04 Ziheng Guo , James Greene , Ming Zhong

Inferring the parameters of ordinary differential equations (ODEs) from noisy observations is an important problem in many scientific fields. Currently, most parameter estimation methods that bypass numerical integration tend to rely on…

Methodology · Statistics 2023-10-25 Mingwei Xu , Samuel W. K. Wong , Peijun Sang

Diffusion models (DMs) are a class of generative machine learning methods that sample a target distribution by transforming samples of a trivial (often Gaussian) distribution using a learned stochastic differential equation. In standard…

Statistical Mechanics · Physics 2024-08-15 Luke Causer , Grant M. Rotskoff , Juan P. Garrahan