English
Related papers

Related papers: Increasing Risk: Dynamic Mean-Preserving Spreads

200 papers

We propose self-diffusion, a novel framework for solving inverse problems without relying on pretrained generative models. Traditional diffusion-based approaches require training a model on a clean dataset to learn to reverse the forward…

Machine Learning · Computer Science 2025-12-09 Guanxiong Luo , Shoujin Huang , Yanlong Yang

In this work, we propose \texttt{TimeGrad}, an autoregressive model for multivariate probabilistic time series forecasting which samples from the data distribution at each time step by estimating its gradient. To this end, we use diffusion…

Machine Learning · Computer Science 2021-07-09 Kashif Rasul , Calvin Seward , Ingmar Schuster , Roland Vollgraf

We consider coupled slow-fast stochastic processes, where the averaged slow motion is given by a two-dimensional Hamiltonian system with multiple critical points. On a proper time scale, the evolution of the first integral converges to a…

Probability · Mathematics 2024-08-07 Shuo Yan

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

Diffusion models cannot enforce hard constraints, yet applications in the physical sciences demand exact satisfaction of conservation laws, boundary conditions, and observational consistency. In this work, we identify a corrector kernel…

Machine Learning · Computer Science 2026-05-14 Omer Rochman-Sharabi , Gilles Louppe

Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive…

Audio and Speech Processing · Electrical Eng. & Systems 2024-03-13 Jean-Marie Lemercier , Julius Richter , Simon Welker , Timo Gerkmann

A novel probabilistic framework for modelling anomalous diffusion is presented. The resulting process is Markovian, non-homogeneous, non-stationary, non-ergodic, and state-dependent. The fundamental law governing this process is driven by…

Mathematical Physics · Physics 2025-03-07 Nestor Barraza , Gabriel Pena , Juliana Gambini , Florencia Carusela

For a general class of diffusion processes with multiplicative noise, describing a variety of physical as well as financial phenomena, mostly typical of complex systems, we obtain the analytical solution for the moments at all times. We…

Statistical Mechanics · Physics 2010-03-18 Giacomo Bormetti , Danilo Delpini

We introduce a class of one dimensional deterministic models of energy-volume conserving interfaces. Numerical simulations show that these dynamics are genuinely super-diffusive. We then modify the dynamics by adding a conservative…

Statistical Mechanics · Physics 2015-05-28 Cédric Bernardin , Gabriel Stoltz

We provide an explicit rigorous derivation of a diffusion limit - a stochastic differential equation with additive noise - from a deterministic skew-product flow. This flow is assumed to exhibit time-scale separation and has the form of a…

Dynamical Systems · Mathematics 2015-05-27 I. Melbourne , A. M. Stuart

We explore a class of hybrid (piecewise deterministic) systems characterized by a large number of individuals inhabiting an environment whose state is described by a set of continuous variables. We use analytical and numerical methods from…

Statistical Mechanics · Physics 2012-09-10 John Realpe-Gomez , Tobias Galla , Alan J. McKane

Dynamical systems driven by a general L\'evy stable noise are considered. The inertia is included and the noise, represented by a generalised Ornstein-Uhlenbeck process, has a finite relaxation time. A general linear problem (the additive…

Statistical Mechanics · Physics 2012-02-15 Tomasz Srokowski

Probabilistic forecasting models for joint distributions of targets in irregular time series with missing values are a heavily under-researched area in machine learning, with, to the best of our knowledge, only two Models have been…

The existence of a global martingale solution to a cross-diffusion system with multiplicative Wiener noise in a bounded domain with no-flux boundary conditions is shown. The model describes the dynamics of population densities of different…

Analysis of PDEs · Mathematics 2022-11-10 Mrinmay Biswas , Ansgar Jüngel

Denoising diffusion models are a popular class of generative models providing state-of-the-art results in many domains. One adds gradually noise to data using a diffusion to transform the data distribution into a Gaussian distribution.…

Machine Learning · Computer Science 2023-08-21 Francisco Vargas , Will Grathwohl , Arnaud Doucet

We analyze diffusion processes with finite propagation speed in a non-homogeneous medium in terms of the heterogeneous telegrapher's equation. In the diffusion limit of infinite-velocity propagation we recover the results for the…

Statistical Mechanics · Physics 2022-11-18 Trifce Sandev , Ljupco Kocarev , Ralf Metzler , Aleksei Chechkin

Recently, score-based generative models have been successfully employed for the task of speech enhancement. A stochastic differential equation is used to model the iterative forward process, where at each step environmental noise and white…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-31 Bunlong Lay , Simon Welker , Julius Richter , Timo Gerkmann

We study diffusion processes driven by a Brownian motion with regular drift in a finite dimension setting. The drift has two components on different time scales, a fast conservative component and a slow dissipative component. Using the…

Probability · Mathematics 2014-03-27 Florent Barret , Max-K. Von Renesse

This paper introduces a novel methodology for the identification of switching dynamics for switched autoregressive linear models. Switching behavior is assumed to follow a Markov model. The system's outputs are contaminated by possibly…

Signal Processing · Electrical Eng. & Systems 2019-03-28 Sarah Hojjatinia , Constantino M. Lagoa

Generative models like diffusion and flow-matching create high-fidelity samples by progressively refining noise. The refinement process is notoriously slow, often requiring hundreds of function evaluations. We introduce Warm-Start Diffusion…

Machine Learning · Computer Science 2025-09-30 Jonas Scholz , Richard E. Turner