English
Related papers

Related papers: Score Shocks: The Burgers Equation Structure of Di…

200 papers

Diffusion models generate samples by reversing a fixed forward diffusion process. Despite already providing impressive empirical results, these diffusion models algorithms can be further improved by reducing the variance of the training…

Machine Learning · Computer Science 2023-02-20 Yilun Xu , Shangyuan Tong , Tommi Jaakkola

In recent years, diffusion models trained on equilibrium molecular distributions have proven effective for sampling biomolecules. Beyond direct sampling, the score of such a model can also be used to derive the forces that act on molecular…

Machine Learning · Computer Science 2026-01-15 Michael Plainer , Hao Wu , Leon Klein , Stephan Günnemann , Frank Noé

Score-based models generate samples by mapping noise to data (and vice versa) via a high-dimensional diffusion process. We question whether it is necessary to run this entire process at high dimensionality and incur all the inconveniences…

Machine Learning · Computer Science 2023-02-28 Bowen Jing , Gabriele Corso , Renato Berlinghieri , Tommi Jaakkola

Following our recent letter, we study in detail an entry-wise diffusion of non-hermitian complex matrices. We obtain an exact partial differential equation (valid for any matrix size $N$ and arbitrary initial conditions) for evolution of…

Mathematical Physics · Physics 2015-10-20 Zdzislaw Burda , Jacek Grela , Maciej A. Nowak , Wojciech Tarnowski , Piotr Warchoł

Symmetry is ubiquitous in many real-world phenomena and tasks, such as physics, images, and molecular simulations. Empirical studies have demonstrated that incorporating symmetries into generative models can provide better generalization…

Machine Learning · Statistics 2026-05-12 Ziyu Chen , Markos A. Katsoulakis , Benjamin J. Zhang

Beyond estimating parameters of interest from data, one of the key goals of statistical inference is to properly quantify uncertainty in these estimates. In Bayesian inference, this uncertainty is provided by the posterior distribution, the…

Machine Learning · Computer Science 2025-01-03 Daniela de Albuquerque , John Pearson

This work introduces a sampling method capable of solving Bayesian inverse problems in function space. It does not assume the log-concavity of the likelihood, meaning that it is compatible with nonlinear inverse problems. The method…

Machine Learning · Statistics 2024-05-27 Lorenzo Baldassari , Ali Siahkoohi , Josselin Garnier , Knut Solna , Maarten V. de Hoop

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 prove that the stochastic Burgers equation, which is related to the Kardar-Parisi-Zhang/KPZ equation via weak derivative, is a "critical" scaling limit for density fluctuations for a family of non-integrable and non-stationary…

Probability · Mathematics 2022-03-01 Kevin Yang

We demonstrate that numerical solutions of Burgers' equation can be obtained by a scale-totality algorithm for fluids of small viscosity (down to one billionth). Two sets of initial data, modelling simple shears and wall boundary layers,…

Fluid Dynamics · Physics 2018-12-20 F. Lam

We consider the stochastically forced Burgers equation with an emphasis on spatially rough driving noise. We show that the law of the process at a fixed time $t$, conditioned on no explosions, is absolutely continuous with respect to the…

Probability · Mathematics 2021-04-16 Jonathan C. Mattingly , Marco Romito , Langxuan Su

The choice of prior is central to solving ill-posed imaging inverse problems, making it essential to select one consistent with the measurements $y$ to avoid severe bias. In Bayesian inverse problems, this could be achieved by evaluating…

Machine Learning · Computer Science 2026-05-01 Frederic Wang , Katherine L. Bouman

We study counterfactual distribution learning for high-dimensional outcomes whose counterfactual law may concentrate near lower-dimensional structure. Standard isotropic smoothing treats all ambient directions equally, leading to…

Methodology · Statistics 2026-05-26 Kwangho Kim

Score-based diffusion models have demonstrated remarkable empirical success in learning high-dimensional distributions, particularly those exhibiting low-dimensional and multi-modal structures. However, theoretical understanding of their…

Machine Learning · Statistics 2026-05-29 Jingda Wu , Changxiao Cai

We analyse how the sampling dynamics of distributions evolve in score-based diffusion models using cross-fluctuations, a centered-moment statistic from statistical physics. Specifically, we show that starting from an unbiased isotropic…

Machine Learning · Computer Science 2026-05-04 Sai Niranjan Ramachandran , Manish Krishan Lal , Suvrit Sra

We present a novel and flexible data-driven framework for estimating the response of higher-order moments of nonlinear stochastic systems to small external perturbations. The classical Generalized Fluctuation--Dissipation Theorem (GFDT)…

Machine Learning · Statistics 2025-08-28 Ludovico T. Giorgini , Fabrizio Falasca , Andre N. Souza

We consider the fractional Burgers' equation on $\R^N$ with the critical dissipation term. We follow the parabolic De-Giorgi's method of Caffarelli and Vasseur \cite{Driftdiffusion} and show existence of smooth solutions given any initial…

Analysis of PDEs · Mathematics 2008-11-10 Chi Hin Chan , Magdalena Czubak

Diffusion Models (DMs), also referred to as score-based diffusion models, utilize neural networks to specify score functions. Unlike most other probabilistic models, DMs directly model the score functions, which makes them more flexible to…

Machine Learning · Computer Science 2023-04-11 Weijian Luo

We study the regularity of the score function in score-based generative models and show that it naturally adapts to the smoothness of the data distribution. Under minimal assumptions, we establish Lipschitz estimates that directly support…

Statistics Theory · Mathematics 2025-06-25 Arthur Stéphanovitch

We give a new algorithm for learning mixtures of $k$ Gaussians (with identity covariance in $\mathbb{R}^n$) to TV error $\varepsilon$, with quasi-polynomial ($O(n^{\text{poly\,log}\left(\frac{n+k}{\varepsilon}\right)})$) time and sample…

Machine Learning · Computer Science 2025-03-05 Khashayar Gatmiry , Jonathan Kelner , Holden Lee