Related papers: Reframing Generative Models for Physical Systems using Stochastic Interpolants

Reframing Generative Models for Physical Systems using Stochastic Interpolants

URL: http://arxiv.org/abs/2509.26282v1
Date: Tue, 30 Sep 2025 14:02:00 GMT
Title: Reframing Generative Models for Physical Systems using Stochastic Interpolants
Authors: Anthony Zhou, Alexander Wikner, Amaury Lancelin, Pedram Hassanzadeh, Amir Barati Farimani,
Abstract summary: Generative models have emerged as powerful surrogates for physical systems, demonstrating increased accuracy, stability, and/or statistical fidelity.<n>Most approaches rely on iteratively denoising a Gaussian, a choice that may not be the most effective for autoregressive prediction tasks in PDEs and dynamical systems such as climate.<n>In this work, we benchmark generative models across diverse physical domains and tasks, and highlight the role of interpolants.
Score: 45.16806809746592
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Generative models have recently emerged as powerful surrogates for physical systems, demonstrating increased accuracy, stability, and/or statistical fidelity. Most approaches rely on iteratively denoising a Gaussian, a choice that may not be the most effective for autoregressive prediction tasks in PDEs and dynamical systems such as climate. In this work, we benchmark generative models across diverse physical domains and tasks, and highlight the role of stochastic interpolants. By directly learning a stochastic process between current and future states, stochastic interpolants can leverage the proximity of successive physical distributions. This allows for generative models that can use fewer sampling steps and produce more accurate predictions than models relying on transporting Gaussian noise. Our experiments suggest that generative models need to balance deterministic accuracy, spectral consistency, and probabilistic calibration, and that stochastic interpolants can potentially fulfill these requirements by adjusting their sampling. This study establishes stochastic interpolants as a competitive baseline for physical emulation and gives insight into the abilities of different generative modeling frameworks.

Related papers

Diffusion models for multivariate subsurface generation and efficient probabilistic inversion [0.0]
Diffusion models offer stable training and state-of-the-art performance for deep generative modeling tasks.<n>We introduce a likelihood approximation accounting for the noise-contamination that is inherent in diffusion modeling.<n>Our tests show significantly improved statistical robustness, enhanced sampling of the posterior probability density function.
arXiv Detail & Related papers (2025-07-21T17:10:16Z)
Physics-aware generative models for turbulent fluid flows through energy-consistent stochastic interpolants [0.0]
Generative models have demonstrated remarkable success in domains such as text, image, and video.<n>In this work, we explore the application of generative models to fluid dynamics, specifically for turbulence simulation.<n>We propose a novel generative model based on interpolants, which enables probabilistic forecasting while incorporating physical constraints.
arXiv Detail & Related papers (2025-04-08T09:29:01Z)
ProGen: Revisiting Probabilistic Spatial-Temporal Time Series Forecasting from a Continuous Generative Perspective Using Stochastic Differential Equations [18.64802090861607]
ProGen Pro provides a robust solution that effectively captures dependencies while managing uncertainty. Our experiments on four benchmark traffic datasets demonstrate that ProGen Pro outperforms state-of-the-art deterministic probabilistic models.
arXiv Detail & Related papers (2024-11-02T14:37:30Z)
Recurrent Interpolants for Probabilistic Time Series Prediction [10.422645245061899]
Sequential models like recurrent neural networks and transformers have become standard for probabilistic time series forecasting. Recent work explores generative approaches using diffusion or flow-based models, extending to time series imputation and forecasting. This work proposes a novel method combining recurrent neural networks' efficiency with diffusion models' probabilistic modeling, based on interpolants and conditional generation with control features.
arXiv Detail & Related papers (2024-09-18T03:52:48Z)
Fusion of Gaussian Processes Predictions with Monte Carlo Sampling [61.31380086717422]
In science and engineering, we often work with models designed for accurate prediction of variables of interest. Recognizing that these models are approximations of reality, it becomes desirable to apply multiple models to the same data and integrate their outcomes.
arXiv Detail & Related papers (2024-03-03T04:21:21Z)
Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
arXiv Detail & Related papers (2024-02-19T15:57:39Z)
Accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networks [0.0]
Generative Adversarial Networks (GANs) have shown immense potential in fields such as text and image generation. Here we quantitatively test this approach by applying it to a prototypical process on a lattice. Importantly, the discreteness of the model is retained despite the noise.
arXiv Detail & Related papers (2023-05-25T10:41:02Z)
Capturing dynamical correlations using implicit neural representations [85.66456606776552]
We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
arXiv Detail & Related papers (2023-04-08T07:55:36Z)
An Energy-Based Prior for Generative Saliency [62.79775297611203]
We propose a novel generative saliency prediction framework that adopts an informative energy-based model as a prior distribution. With the generative saliency model, we can obtain a pixel-wise uncertainty map from an image, indicating model confidence in the saliency prediction. Experimental results show that our generative saliency model with an energy-based prior can achieve not only accurate saliency predictions but also reliable uncertainty maps consistent with human perception.
arXiv Detail & Related papers (2022-04-19T10:51:00Z)
Stochastic Parameterizations: Better Modelling of Temporal Correlations using Probabilistic Machine Learning [1.5293427903448025]
We show that by using a physically-informed recurrent neural network within a probabilistic framework, our model for the 96 atmospheric simulation is competitive. This is due to a superior ability to model temporal correlations compared to standard first-order autoregressive schemes. We evaluate across a number of metrics from the literature, but also discuss how the probabilistic metric of likelihood may be a unifying choice for future climate models.
arXiv Detail & Related papers (2022-03-28T14:51:42Z)
Multiplicative noise and heavy tails in stochastic optimization [62.993432503309485]
empirical optimization is central to modern machine learning, but its role in its success is still unclear. We show that it commonly arises in parameters of discrete multiplicative noise due to variance. A detailed analysis is conducted in which we describe on key factors, including recent step size, and data, all exhibit similar results on state-of-the-art neural network models.
arXiv Detail & Related papers (2020-06-11T09:58:01Z)

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