English
Related papers

Related papers: A Class of Infinite Dimensional Diffusion Processe…

200 papers

We propose an additional category of dimensionless groups based on the principle of {\it entropic similarity}, defined by ratios of (i) entropy production terms; (ii) entropy flow rates or fluxes; or (iii) information flow rates or fluxes.…

Fluid Dynamics · Physics 2023-01-31 Robert K. Niven

We introduce Functional Diffusion Processes (FDPs), which generalize score-based diffusion models to infinite-dimensional function spaces. FDPs require a new mathematical framework to describe the forward and backward dynamics, and several…

Machine Learning · Computer Science 2023-12-19 Giulio Franzese , Giulio Corallo , Simone Rossi , Markus Heinonen , Maurizio Filippone , Pietro Michiardi

We propose a general approach for quantitative convergence analysis of non-reversible Markov processes, based on the concept of second-order lifts and a variational approach to hypocoercivity. To this end, we introduce the flow Poincar{\'e}…

Analysis of PDEs · Mathematics 2025-07-22 Andreas Eberle , Arnaud Guillin , Leo Hahn , Francis Lörler , Manon Michel

We consider the problem of learning two families of time-evolving random measures from indirect observations. In the first model, the signal is a Fleming--Viot diffusion, which is reversible with respect to the law of a Dirichlet process,…

Statistics Theory · Mathematics 2014-11-19 Omiros Papaspiliopoulos , Matteo Ruggiero , Dario Spanò

Discrete-time diffusion-based generative models and score matching methods have shown promising results in modeling high-dimensional image data. Recently, Song et al. (2021) show that diffusion processes that transform data into noise can…

Machine Learning · Computer Science 2021-10-01 Chin-Wei Huang , Jae Hyun Lim , Aaron Courville

We consider a diffusion process in $\mathbb{R}^d$ with a generator of the form $ L:=\frac 12 e^{V(x)}div(e^{-V(x)}\nabla ) $ where $V$ is measurable and periodic. We only assume that $e^V$ and $e^{-V}$ are locally integrable. We then show…

Probability · Mathematics 2016-01-13 Moustapha Ba , Pierre Mathieu

Denoising diffusion models have proven to be a flexible and effective paradigm for generative modelling. Their recent extension to infinite dimensional Euclidean spaces has allowed for the modelling of stochastic processes. However, many…

Dyson's model in infinite dimensions is a system of Brownian particles interacting via a logarithmic potential with an inverse temperature of $ \beta = 2$. The stochastic process is given as a solution to an infinite-dimensional stochastic…

Probability · Mathematics 2022-01-03 Hirofumi Osada , Ryosuke Tsuboi

We consider a class of infinite-dimensional diffusions where the interaction between the components is both spatial and temporal. We start the system from a Gibbs measure with finite-range uniformly bounded interaction. Under suitable…

Probability · Mathematics 2015-05-14 F. Redig , S. Roelly , W. Ruszel

Drawing from the theory of stochastic differential equations, we introduce a novel sampling method for known distributions and a new algorithm for diffusion generative models with unknown distributions. Our approach is inspired by the…

Statistics Theory · Mathematics 2024-07-12 Xicheng Zhang

The present paper originated from our previous study of the problem of harmonic analysis on the infinite symmetric group. This problem leads to a family {P_z} of probability measures, the z-measures, which depend on the complex parameter z.…

Probability · Mathematics 2009-02-15 Alexei Borodin , Grigori Olshanski

Classes of multivariate and cone valued infinitely divisible Gamma distributions are introduced. Particular emphasis is put on the cone-valued case, due to the relevance of infinitely divisible distributions on the positive semi-definite…

Probability · Mathematics 2015-03-19 Victor Pérez-Abreu , Robert Stelzer

In this work we would like to point out the possibility of generating a class of exactly solvable convection-diffusion-reaction equation in similarity form with intrinsic supersymmetry, i.e., the solution and the diffusion coefficient of…

Mathematical Physics · Physics 2024-09-17 Choon-Lin Ho

We construct a recurrent diffusion process with values in the space of probability measures over an arbitrary closed Riemannian manifold of dimension $d\ge 2$. The process is associated with the Dirichlet form defined by integration of the…

Probability · Mathematics 2022-04-04 L. Dello Schiavo

We introduce a new class of nonparametric prior distributions on the space of continuously varying densities, induced by Dirichlet process mixtures which diffuse in time. These select time-indexed random functions without jumps, whose…

Methodology · Statistics 2016-02-10 Ramsés H. Mena , Matteo Ruggiero

We present a nonparametric prior over reversible Markov chains. We use completely random measures, specifically gamma processes, to construct a countably infinite graph with weighted edges. By enforcing symmetry to make the edges undirected…

Machine Learning · Statistics 2014-03-18 Konstantina Palla , David A. Knowles , Zoubin Ghahramani

In this paper we look at the properties of limits of a sequence of real valued time inhomogeneous diffusions. When convergence is only in the sense of finite-dimensional distributions then the limit does not have to be a diffusion. However,…

Probability · Mathematics 2009-05-14 George Lowther

We investigate free-energy dissipation in a continuous-time birth-and-death dynamics in $\mathbb{R}^d$. For these Markov processes, the class of reversible measures coincides with the infinite-volume Gibbs point processes for some…

Probability · Mathematics 2026-02-17 Benedikt Jahnel , Jonas Köppl , Yannic Steenbeck , Alexander Zass

Most of the previous studies on the well-known Gray-Scott model view it as an irreversible chemical reaction system. In this paper, we derive a four-species reaction-diffusion system using the energetic variational approach based on the law…

Analysis of PDEs · Mathematics 2022-04-01 Jiangyan Liang , Ning Jiang , Chun Liu , Yiwei Wang , Teng-Fei Zhang

Deep generative models have become a standard for modeling priors for inverse problems, going beyond classical sparsity-based methods. However, existing theoretical guarantees are mostly confined to finite-dimensional vector spaces,…

Numerical Analysis · Mathematics 2026-03-04 Paolo Angella , Vito Paolo Pastore , Matteo Santacesaria