English
Related papers

Related papers: Diffusion Models under Alternative Noise: Simplifi…

200 papers

We study statistical inference for small-noise-perturbed multiscale dynamical systems under the assumption that we observe a single time series from the slow process only. We construct estimators for both averaging and homogenization…

Probability · Mathematics 2018-09-13 Siragan Gailus , Konstantinos Spiliopoulos

In this paper, we first establish well-posedness of McKean-Vlasov stochastic differential equations (McKean-Vlasov SDEs) with common noise, possibly with coefficients having super-linear growth in the state variable. Second, we present…

Probability · Mathematics 2020-06-02 Chaman Kumar , Neelima , Christoph Reisinger , Wolfgang Stockinger

Diffusion-based generative models use stochastic differential equations (SDEs) and their equivalent ordinary differential equations (ODEs) to establish a smooth connection between a complex data distribution and a tractable prior…

Machine Learning · Computer Science 2024-08-25 Defang Chen , Zhenyu Zhou , Can Wang , Chunhua Shen , Siwei Lyu

This work explores the theoretical and practical foundations of denoising diffusion probabilistic models (DDPMs) and score-based generative models, which leverage stochastic processes and Brownian motion to model complex data distributions.…

Machine Learning · Computer Science 2024-12-30 Jathin Korrapati , Tanish Baranwal , Rahul Shah

We investigate the convergence rate for the time discretization of a class of quadratic backward SDEs -- potentially involving path-dependent terminal values -- when coupled with non-standard Lipschitz-type forward SDEs. In our review of…

Probability · Mathematics 2024-12-12 Rhoss Likibi Pellat , Emmanuel Che Fonka , Olivier Menoukeu Pamen

This study addresses the inverse problem of parameter estimation for Stochastic Differential Equations (SDEs) by minimizing a regularized discrepancy functional via Stochastic Gradient Descent (SGD). To achieve computational efficiency, we…

Machine Learning · Statistics 2026-03-31 Francisco Delgado-Vences , José Julián Pavón-Español , Arelly Ornelas

We study a discrete denoising diffusion framework that integrates a sample-efficient estimator of single-site conditionals with round-robin noising and denoising dynamics for generative modeling over discrete state spaces. Rather than…

Machine Learning · Computer Science 2026-03-02 Karthik Elamvazhuthi , Abhijith Jayakumar , Andrey Y. Lokhov

We study the large deviations principle for locally periodic stochastic differential equations with small noise and fast oscillating coefficients. There are three possible regimes depending on how fast the intensity of the noise goes to…

Probability · Mathematics 2012-04-05 Paul Dupuis , Konstantinos Spiliopoulos

Partial Differential Equation (PDE)-based approaches have gained significant attention in image despeckling due to their strong capability to preserve structural details while suppressing noise. However, conventional second-order PDE models…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Manish Kumar , Rajendra K. Ray

Denoising is intuitively related to projection. Indeed, under the manifold hypothesis, adding random noise is approximately equivalent to orthogonal perturbation. Hence, learning to denoise is approximately learning to project. In this…

Machine Learning · Computer Science 2024-06-04 Frank Permenter , Chenyang Yuan

We discrete the ergodic semilinear stochastic partial differential equations in space dimension $d \leq 3$ with additive noise, spatially by a spectral Galerkin method and temporally by an exponential Euler scheme. It is shown that both the…

Numerical Analysis · Mathematics 2020-06-16 Ziheng Chen , Siqing Gan , Xiaojie Wang

We study distribution dependent stochastic differential equation driven by a continuous process, without any specification on its law, following the approach initiated in [16]. We provide several criteria for existence and uniqueness of…

Probability · Mathematics 2022-03-07 Lucio Galeati , Fabian A. Harang , Avi Mayorcas

We consider the problem of mean estimation assuming only finite variance. We study a new class of mean estimators constructed by integrating over random noise applied to a soft-truncated empirical mean estimator. For appropriate choices of…

Statistics Theory · Mathematics 2019-06-26 Matthew J. Holland

Score-based generative modeling (SGM) has grown to be a hugely successful method for learning to generate samples from complex data distributions such as that of images and audio. It is based on evolving an SDE that transforms white noise…

Machine Learning · Computer Science 2022-10-04 Holden Lee , Jianfeng Lu , Yixin Tan

We demonstrate how to model the toppling activity in avalanching systems by stochastic differential equations (SDEs). The theory is developed as a generalization of the classical mean field approach to sandpile dynamics by formulating it as…

Adaptation and Self-Organizing Systems · Physics 2009-11-13 Martin Rypdal , Kristoffer Rypdal

This paper concerns the McKean-Vlasov stochastic differential equation (SDE) with common noise. An appropriate definition of a weak solution to such an equation is developed. The importance of the notion of compatibility in this definition…

Probability · Mathematics 2020-06-29 William R. P. Hammersley , David Šiška , Łukasz Szpruch

We construct a nonstandard finite difference numerical scheme to approximate stochastic differential equations (SDEs) using the idea of weighed step introduced by R.E. Mickens. We prove the strong convergence of our scheme under locally…

Numerical Analysis · Mathematics 2015-07-23 Frédéric Pierret

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

Stochastic differential equations (SDEs) are a staple of mathematical modelling of temporal dynamics. However, a fundamental limitation has been that such models have typically been relatively inflexible, which recent work introducing…

Machine Learning · Computer Science 2021-05-12 Patrick Kidger , James Foster , Xuechen Li , Harald Oberhauser , Terry Lyons

Inverse problems describe the process of estimating the causal factors from a set of measurements or data. Mapping of often incomplete or degraded data to parameters is ill-posed, thus data-driven iterative solutions are required, for…

Artificial Intelligence · Computer Science 2024-06-21 Weitong Zhang , Chengqi Zang , Liu Li , Sarah Cechnicka , Cheng Ouyang , Bernhard Kainz