English
Related papers

Related papers: Structure-Aware Variational Learning of a Class of…

200 papers

Energy-based models are a simple yet powerful class of probabilistic models, but their widespread adoption has been limited by the computational burden of training them. We propose a novel loss function called Energy Discrepancy (ED) which…

Machine Learning · Statistics 2023-11-28 Tobias Schröder , Zijing Ou , Jen Ning Lim , Yingzhen Li , Sebastian J. Vollmer , Andrew B. Duncan

We propose a methodology that combines generative latent diffusion models with physics-informed machine learning to generate solutions of parametric partial differential equations (PDEs) conditioned on partial observations, which includes,…

Machine Learning · Computer Science 2026-02-11 Davide Gallon , Philippe von Wurstemberger , Patrick Cheridito , Arnulf Jentzen

This paper develops a comprehensive mathematical framework for energy-based modeling of physical systems, with particular emphasis on preserving fundamental structural properties throughout the modeling and discretization process. The…

Numerical Analysis · Mathematics 2025-12-11 M. H. M Rashid

Traditional energy-based learning models associate a single energy metric to each configuration of variables involved in the underlying optimization process. Such models associate the lowest energy state to the optimal configuration of…

Machine Learning · Computer Science 2020-04-10 Oindrila Chatterjee , Shantanu Chakrabartty

We present a novel simulation-free framework for training continuous-time diffusion processes over very general objective functions. Existing methods typically involve either prescribing the optimal diffusion process -- which only works for…

Machine Learning · Computer Science 2025-06-24 Mengjian Hua , Eric Vanden-Eijnden , Ricky T. Q. Chen

The influence of dissipation on the fluctuation statistics of the total energy is investigated through both a phenomenological and a stochastic model for dissipative energy-transfer through a cascade of states. In equilibrium the states…

Statistical Mechanics · Physics 2013-06-27 Eric Bertin , Peter C. W. Holdsworth

With the rapid development of computational techniques and scientific tools, great progress of data-driven analysis has been made to extract governing laws of dynamical systems from data. Despite the wide occurrences of non-Gaussian…

Dynamical Systems · Mathematics 2022-10-12 Yubin Lu , Yang Li , Jinqiao Duan

This paper aims to investigate the diffusion behavior of particles moving in stochastic flows under a structure-preserving scheme. We compute the effective diffusivity for normal diffusive random flows and establish the power law between…

Numerical Analysis · Mathematics 2024-05-30 Tan Zhang , Zhongjian Wang , Jack Xin , Zhiwen Zhang

We present Epistemic Variational Onsager Diffusion Models (EVODMs), a machine learning framework that integrates Onsager's variational principle with diffusion models to enable thermodynamically consistent learning of free energy and…

Computational Physics · Physics 2025-02-18 Zequn He , Celia Reina

This paper deals with the analysis of stochastic systems which can be described by a Langevin equation. By the method presented in this paper drift and diffusion terms of the corresponding Fokker-Planck equation can be extracted from the…

Condensed Matter · Physics 2009-10-31 S. Siegert , R. Friedrich , J. Peinke

The reconstruction and inference of stochastic dynamical systems from data is a fundamental task in inverse problems and statistical learning. While surrogate modeling advances computational methods to approximate these dynamics, standard…

Optimization and Control · Mathematics 2026-04-14 Nicole Tianjiao Yang

We study a class of stochastic evolution equations with a dissipative forcing nonlinearity and additive noise. The noise is assumed to satisfy rather general assumptions about the form of the covariance function; our framework covers…

Probability · Mathematics 2009-11-23 Stefano Bonaccorsi , Ciprian Tudor

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

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 propose a new method for spatio-temporal forecasting on arbitrarily distributed points. Assuming that the observed system follows an unknown partial differential equation, we derive a continuous-time model for the dynamics of the data…

Machine Learning · Computer Science 2022-03-18 Marten Lienen , Stephan Günnemann

In this work, we study the generalizability of diffusion models by looking into the hidden properties of the learned score functions, which are essentially a series of deep denoisers trained on various noise levels. We observe that as…

Machine Learning · Computer Science 2024-12-03 Xiang Li , Yixiang Dai , Qing Qu

We introduce a robust framework for learning various generalized Hamiltonian dynamics from noisy, sparse phase-space data and in an unsupervised manner based on variational Bayesian inference. Although conservative, dissipative, and…

Machine Learning · Computer Science 2025-09-10 Luke McLennan , Yi Wang , Ryan Farell , Minh Nguyen , Chandrajit Bajaj

Accurate state estimation requires careful consideration of uncertainty surrounding the process and measurement models; these characteristics are usually not well-known and need an experienced designer to select the covariance matrices. An…

Machine Learning · Statistics 2025-07-18 Pardha Sai Krishna Ala , Ameya Salvi , Venkat Krovi , Matthias Schmid

In the first part of this paper, we consider a family of continuous-time dynamical systems coupled with diffusion-transmutation processes. Under certain conditions, such randomly perturbed dynamical systems can be interpreted as an averaged…

Optimization and Control · Mathematics 2024-08-21 Getachew K. Befekadu

Energy-based learning is a powerful framework for generative modelling, but its training is inherently non-convex, leading potentially to sensitivity to initialisation, poor local optima, and unstable gradient dynamics. We present a…

Machine Learning · Computer Science 2026-05-11 Aurélien Decelle , Alfonso de Jesús Navas Gómez , Beatriz Seoane