Energy Loss Functions for Physical Systems

• URL: http://arxiv.org/abs/2511.02087v1
• Date: Mon, 03 Nov 2025 21:58:36 GMT
• Title: Energy Loss Functions for Physical Systems
• Authors: Sékou-Oumar Kaba, Kusha Sareen, Daniel Levy, Siamak Ravanbakhsh,
• Abstract summary: 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.
• Score: 16.10782090682612
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Effectively leveraging prior knowledge of a system's physics is crucial for applications of machine learning to scientific domains. Previous approaches mostly focused on incorporating physical insights at the architectural level. In this paper, we propose a framework to leverage physical information directly into the loss function for prediction and generative modeling tasks on systems like molecules and spins. We derive energy loss functions assuming that each data sample is in thermal equilibrium with respect to an approximate energy landscape. By using the reverse KL divergence with a Boltzmann distribution around the data, we obtain the loss as an energy difference between the data and the model predictions. This perspective also recasts traditional objectives like MSE as energy-based, but with a physically meaningless energy. In contrast, our formulation yields physically grounded loss functions with gradients that better align with valid configurations, while being architecture-agnostic and computationally efficient. The energy loss functions also inherently respect physical symmetries. We demonstrate our approach on molecular generation and spin ground-state prediction and report significant improvements over baselines.

Related papers

• APRIL: Auxiliary Physically-Redundant Information in Loss - A physics-informed framework for parameter estimation with a gravitational-wave case study [0.0]
  Physics-Informed Neural Networks (PINNs) embed the partial differential equations governing the system under study directly into the training of Neural Networks.<n>We present a complementary approach by including auxiliary physically-redundant information in loss.<n>We mathematically demonstrate that these terms preserve the true physical minimum while reshaping the loss landscape.
  arXiv  Detail & Related papers  (2025-10-15T15:34:19Z)
• From Physics to Machine Learning and Back: Part II - Learning and Observational Bias in PHM [52.64097278841485]
  Review examines how incorporating learning and observational biases through physics-informed modeling and data strategies can guide models toward physically consistent and reliable predictions.<n>Fast adaptation methods including meta-learning and few-shot learning are reviewed alongside domain generalization techniques.
  arXiv  Detail & Related papers  (2025-09-25T14:15:43Z)
• Learning with springs and sticks [6.765839157891597]
  We study a simple dynamical system composed of springs and sticks capable of arbitrarily approximating any continuous function.<n>We apply the proposed simulation system to regression tasks and show that its performance is comparable to that of multi-layer perceptrons.<n>We empirically find a emphthermodynamic learning barrier for the system caused by the fluctuations of the environment.
  arXiv  Detail & Related papers  (2025-08-26T13:26:26Z)
• FIRE-GNN: Force-informed, Relaxed Equivariance Graph Neural Network for Rapid and Accurate Prediction of Surface Properties [8.537263229630897]
  We introduce FIRE-GNN, which integrates surface-normal symmetry breaking and machine learning interatomic potential (MLIP)-derived force information.<n>It achieves a twofold reduction in mean absolute error (down to 0.065 eV) over the previous state-of-the-art for work function prediction.<n>This model enables accurate and rapid predictions of the work function and cleavage energy across a vast chemical space.
  arXiv  Detail & Related papers  (2025-08-22T00:07:52Z)
• Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised Learning [27.544116710935278]
  Energy landscapes play a crucial role in shaping dynamics of many real-world complex systems.<n>We propose a physics-informed self-supervised learning method to learn the energy landscape from the evolution trajectories of the system.
  arXiv  Detail & Related papers  (2025-02-24T04:26:26Z)
• DimINO: Dimension-Informed Neural Operator Learning [41.37905663176428]
  DimINO is a framework inspired by dimensional analysis.<n>It can be seamlessly integrated into existing neural operator architectures.<n>It achieves up to 76.3% performance gain on PDE datasets.
  arXiv  Detail & Related papers  (2024-10-08T10:48:50Z)
• Thermodynamics-Consistent Graph Neural Networks [50.0791489606211]
  We propose excess Gibbs free energy graph neural networks (GE-GNNs) for predicting composition-dependent activity coefficients of binary mixtures. The GE-GNN architecture ensures thermodynamic consistency by predicting the molar excess Gibbs free energy. We demonstrate high accuracy and thermodynamic consistency of the activity coefficient predictions.
  arXiv  Detail & Related papers  (2024-07-08T06:58:56Z)
• PhyRecon: Physically Plausible Neural Scene Reconstruction [81.73129450090684]
  We introduce PHYRECON, the first approach to leverage both differentiable rendering and differentiable physics simulation to learn implicit surface representations. Central to this design is an efficient transformation between SDF-based implicit representations and explicit surface points. Our results also exhibit superior physical stability in physical simulators, with at least a 40% improvement across all datasets.
  arXiv  Detail & Related papers  (2024-04-25T15:06:58Z)
• On the importance of catalyst-adsorbate 3D interactions for relaxed energy predictions [98.70797778496366]
  We investigate whether it is possible to predict a system's relaxed energy in the OC20 dataset while ignoring the relative position of the adsorbate. We find that while removing binding site information impairs accuracy as expected, modified models are able to predict relaxed energies with remarkably decent MAE.
  arXiv  Detail & Related papers  (2023-10-10T14:57:04Z)
• Energy Transformer [64.22957136952725]
  Our work combines aspects of three promising paradigms in machine learning, namely, attention mechanism, energy-based models, and associative memory. We propose a novel architecture, called the Energy Transformer (or ET for short), that uses a sequence of attention layers that are purposely designed to minimize a specifically engineered energy function.
  arXiv  Detail & Related papers  (2023-02-14T18:51:22Z)
• A physics-based domain adaptation framework for modelling and forecasting building energy systems [5.8010446129208155]
  State-of-the-art machine-learning-based models are a popular choice for modeling and forecasting energy behavior in buildings. However, their architecture does not hold physical to mechanistic structures linked with governing physical phenomena. We introduce a novel SDA approach where instead of labeled data, we leverage the geometric structure of the LTI governed by heat transfer ordinary differential equations.
  arXiv  Detail & Related papers  (2022-08-19T17:27:39Z)
• Data vs. Physics: The Apparent Pareto Front of Physics-Informed Neural Networks [8.487185704099925]
  Physics-informed neural networks (PINNs) have emerged as a promising deep learning method. PINNs are difficult to train and often require a careful tuning of loss weights when data and physics loss functions are combined.
  arXiv  Detail & Related papers  (2021-05-03T13:47:45Z)
• Causal Discovery in Physical Systems from Videos [123.79211190669821]
  Causal discovery is at the core of human cognition. We consider the task of causal discovery from videos in an end-to-end fashion without supervision on the ground-truth graph structure.
  arXiv  Detail & Related papers  (2020-07-01T17:29:57Z)
• Targeted free energy estimation via learned mappings [66.20146549150475]
  Free energy perturbation (FEP) was proposed by Zwanzig more than six decades ago as a method to estimate free energy differences. FEP suffers from a severe limitation: the requirement of sufficient overlap between distributions. One strategy to mitigate this problem, called Targeted Free Energy Perturbation, uses a high-dimensional mapping in configuration space to increase overlap.
  arXiv  Detail & Related papers  (2020-02-12T11:10:00Z)

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.