Structure-Aware Variational Learning of a Class of Generalized Diffusions

• URL: http://arxiv.org/abs/2604.20188v1
• Date: Wed, 22 Apr 2026 05:05:54 GMT
• Title: Structure-Aware Variational Learning of a Class of Generalized Diffusions
• Abstract summary: Learning the underlying potential energy of gradient systems from partial and noisy observations is a fundamental problem arising in physics, chemistry, and data-driven modeling.<n>We propose a structure-aware, energy-based learning framework for inferring unknown potential functions in generalized diffusion processes.<n>We demonstrate that the proposed energy-based loss exhibits enhanced robustness with respect to observation time, noise level, and the diversity and amount of available training data.
• Score: 12.63619588531119
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning the underlying potential energy of stochastic gradient systems from partial and noisy observations is a fundamental problem arising in physics, chemistry, and data-driven modeling. Classical approaches often rely on direct regression of governing equations or velocity fields, which can be sensitive to noise and external perturbations and may fail when observations are incomplete. In this work, we propose a structure-aware, energy-based learning framework for inferring unknown potential functions in generalized diffusion processes, grounded in the energetic variational approach. Starting from the energy-dissipation law associated with the Fokker-Planck equation, we construct loss functions based on the De Giorgi dissipation functional, which consistently couple the free energy and the dissipation mechanism of the system. This formulation avoids explicit enforcement of the governing partial differential equation and preserves the underlying variational structure of the dynamics. Through numerical experiments in one, two, and three dimensions, we demonstrate that the proposed energy-based loss exhibits enhanced robustness with respect to observation time, noise level, and the diversity and amount of available training data. These results highlight the effectiveness of energy-dissipation principles as a reliable foundation for learning stochastic diffusion dynamics from data.

Related papers

• Data-driven discovery of governing differential equations across physical systems [61.522420798136984]
  We propose a problem-oriented perspective on data-driven differential equation discovery.<n>We first introduce a two-dimensional phase diagram of equation discoverability.<n>We then present the representation-evaluation-optimization (REO) framework as a fundamental abstraction of the discovery process.
  arXiv  Detail & Related papers  (2026-06-08T15:35:06Z)
• EFF-Grasp: Energy-Field Flow Matching for Physics-Aware Dexterous Grasp Generation [54.09734511705173]
  EFF-Grasp is a Flow-Matching synthesis-based framework for physics-aware dexterous grasp generation.<n>We reformulate grasp as a deterministic ordinary differential equation (ODE) process, which enables efficient and stable generation through smooth probability flows.<n> EFF-Grasp achieves superior performance in grasp quality and physical feasibility, while requiring substantially fewer sampling steps than diffusion-based baselines.
  arXiv  Detail & Related papers  (2026-03-17T06:11:56Z)
• Physics as the Inductive Bias for Causal Discovery [7.9653270330458446]
  Causal discovery is often a data-driven paradigm to analyze complex real-world systems.<n>We develop a scalable sparsity-inducing MLE algorithm that exploits causal graph structure for efficient parameter estimation.
  arXiv  Detail & Related papers  (2026-02-03T23:42:01Z)
• GIMLET: Generalizable and Interpretable Model Learning through Embedded Thermodynamics [4.032628442222966]
  We develop a data-driven framework for discovering relations in models of fluid flow and scalar transport.<n>Under the assumption that velocity and/or scalar fields are measured, our approach infers unknown closure terms in the governing equations as neural networks.<n>The framework is demonstrated on several benchmark systems, including the Burgers equation, the Kuramoto-Sivashinsky equation, and the incompressible Navier--Stokes equations for both Newtonian and non-Newtonian fluids.
  arXiv  Detail & Related papers  (2025-12-22T23:50:17Z)
• Energy Loss Functions for Physical Systems [16.10782090682612]
  We propose a framework to leverage physical information directly into the loss function for prediction and generative modeling tasks.<n>We demonstrate our approach on molecular generation and spin ground-state prediction and report significant improvements over baselines.
  arXiv  Detail & Related papers  (2025-11-03T21:58:36Z)
• Identifiable learning of dissipative dynamics [25.409059056398124]
  We introduce I-OnsagerNet, a neural framework that learns dissipative dynamics directly from trajectories.<n>I-OnsagerNet extends the Onsager principle to guarantee that the learned potential is obtained from the stationary density.<n>Our approach enables us to calculate the entropy production and to quantify irreversibility, offering a principled way to detect and quantify deviations from equilibrium.
  arXiv  Detail & Related papers  (2025-10-28T07:57:14Z)
• Learning Stochastic Thermodynamics Directly from Correlation and Trajectory-Fluctuation Currents [0.0]
  Currents have recently gained increased attention for their role in bounding entropy production.<n>We introduce a fundamental relationship between the cumulant currents there and standard machine-learning loss functions.<n>These loss functions reproduce results derived both from TURs and other methods.<n>More significantly, they open a path to discover new loss functions for previously inaccessible quantities.
  arXiv  Detail & Related papers  (2025-04-26T19:42:09Z)
• Transformers from Diffusion: A Unified Framework for Neural Message Passing [79.9193447649011]
  Message passing neural networks (MPNNs) have become a de facto class of model solutions.<n>We propose an energy-constrained diffusion model, which integrates the inductive bias of diffusion with layer-wise constraints of energy.<n>Building on these insights, we devise a new class of message passing models, dubbed Transformers (DIFFormer), whose global attention layers are derived from the principled energy-constrained diffusion framework.
  arXiv  Detail & Related papers  (2024-09-13T17:54:41Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)
• Decimation technique for open quantum systems: a case study with driven-dissipative bosonic chains [62.997667081978825]
  Unavoidable coupling of quantum systems to external degrees of freedom leads to dissipative (non-unitary) dynamics. We introduce a method to deal with these systems based on the calculation of (dissipative) lattice Green's function. We illustrate the power of this method with several examples of driven-dissipative bosonic chains of increasing complexity.
  arXiv  Detail & Related papers  (2022-02-15T19:00:09Z)
• Structure-Preserving Learning Using Gaussian Processes and Variational Integrators [62.31425348954686]
  We propose the combination of a variational integrator for the nominal dynamics of a mechanical system and learning residual dynamics with Gaussian process regression. We extend our approach to systems with known kinematic constraints and provide formal bounds on the prediction uncertainty.
  arXiv  Detail & Related papers  (2021-12-10T11:09:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.