In-Context Learning of Stochastic Differential Equations with Foundation Inference Models

• URL: http://arxiv.org/abs/2502.19049v2
• Date: Tue, 21 Oct 2025 16:08:49 GMT
• Title: In-Context Learning of Stochastic Differential Equations with Foundation Inference Models
• Authors: Patrick Seifner, Kostadin Cvejoski, David Berghaus, Cesar Ojeda, Ramses J. Sanchez,
• Abstract summary: differential equations (SDEs) describe dynamical systems where deterministic flows, governed by a drift function, are superimposed with random fluctuations, dictated by a diffusion function.<n>We introduce FIM-SDE (Foundation Inference Model for SDEs), a pretrained recognition model that delivers accurate in-context estimation of the drift and diffusion functions of low-dimensional SDEs.<n>We demonstrate that FIM-SDE achieves robust in-context function estimation across a wide range of synthetic and real-world processes.
• Score: 6.785438664749581
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Stochastic differential equations (SDEs) describe dynamical systems where deterministic flows, governed by a drift function, are superimposed with random fluctuations, dictated by a diffusion function. The accurate estimation (or discovery) of these functions from data is a central problem in machine learning, with wide application across the natural and social sciences. Yet current solutions either rely heavily on prior knowledge of the dynamics or involve intricate training procedures. We introduce FIM-SDE (Foundation Inference Model for SDEs), a pretrained recognition model that delivers accurate in-context (or zero-shot) estimation of the drift and diffusion functions of low-dimensional SDEs, from noisy time series data, and allows rapid finetuning to target datasets. Leveraging concepts from amortized inference and neural operators, we (pre)train FIM-SDE in a supervised fashion to map a large set of noisy, discretely observed SDE paths onto the space of drift and diffusion functions. We demonstrate that FIM-SDE achieves robust in-context function estimation across a wide range of synthetic and real-world processes -- from canonical SDE systems (e.g., double-well dynamics or weakly perturbed Lorenz attractors) to stock price recordings and oil-price and wind-speed fluctuations -- while matching the performance of symbolic, Gaussian process and Neural SDE baselines trained on the target datasets. When finetuned to the target processes, we show that FIM-SDE consistently outperforms all these baselines.

Related papers

• Stochastic Deep Learning: A Probabilistic Framework for Modeling Uncertainty in Structured Temporal Data [0.0]
  I propose a novel framework that integrates differential equations (SDEs) with deep generative models to improve uncertainty in machine learning applications involving structured and temporal data.<n>This approach, termed Latent Differential Inference (SLDI), embeds an It SDE in the latent space of a variational autoencoder.<n>The drift and diffusion terms of the SDE are parameterized by neural networks, enabling data-driven inference and generalizing classical time series models to handle irregular sampling and complex dynamic structure.
  arXiv  Detail & Related papers  (2026-01-08T18:53:59Z)
• Expanding the Chaos: Neural Operator for Stochastic (Partial) Differential Equations [65.80144621950981]
  We build on Wiener chaos expansions (WCE) to design neural operator (NO) architectures for SPDEs and SDEs.<n>We show that WCE-based neural operators provide a practical and scalable way to learn SDE/SPDE solution operators.
  arXiv  Detail & Related papers  (2026-01-03T00:59:25Z)
• SING: SDE Inference via Natural Gradients [0.0]
  We propose SDE Inference via Natural Gradients (SING) to efficiently exploit the underlying geometry of the model and variational posterior.<n>SING enables fast and reliable inference in latent SDE models by approximating intractable integrals and parallelizing computations in time.<n>We show that SING outperforms prior methods in state inference and drift estimation on a variety of datasets.
  arXiv  Detail & Related papers  (2025-06-21T19:36:11Z)
• Physics-informed Reduced Order Modeling of Time-dependent PDEs via Differentiable Solvers [1.224954637705144]
  We propose Physics-informed ROM ($Phi$-ROM) by incorporating differentiable PDE solvers into the training procedure.<n>Our model outperforms state-of-the-art data-driven ROMs and other physics-informed strategies.<n>$Phi$-ROM learns to recover and forecast the solution fields even when trained or evaluated with sparse and irregular observations of the fields.
  arXiv  Detail & Related papers  (2025-05-20T16:47:04Z)
• Paving the way for scientific foundation models: enhancing generalization and robustness in PDEs with constraint-aware pre-training [49.8035317670223]
  A scientific foundation model (SciFM) is emerging as a promising tool for learning transferable representations across diverse domains.<n>We propose incorporating PDE residuals into pre-training either as the sole learning signal or in combination with data loss to compensate for limited or infeasible training data.<n>Our results show that pre-training with PDE constraints significantly enhances generalization, outperforming models trained solely on solution data.
  arXiv  Detail & Related papers  (2025-03-24T19:12:39Z)
• Principled model selection for stochastic dynamics [0.0]
  PASTIS is a principled method combining likelihood-estimation statistics with extreme value theory to suppress superfluous parameters.<n>It reliably identifies minimal models, even with low sampling rates or measurement error.<n>It applies to partial differential equations, and applies to ecological networks and reaction-diffusion dynamics.
  arXiv  Detail & Related papers  (2025-01-17T18:23:16Z)
• A Data-Driven Framework for Discovering Fractional Differential Equations in Complex Systems [8.206685537936078]
  This study introduces a stepwise data-driven framework for discovering fractional differential equations (FDEs) directly from data.<n>Our framework applies deep neural networks as surrogate models for denoising and reconstructing sparse and noisy observations.<n>We validate the framework across various datasets, including synthetic anomalous diffusion data and experimental data on the creep behavior of frozen soils.
  arXiv  Detail & Related papers  (2024-12-05T08:38:30Z)
• Advancing Generalization in PINNs through Latent-Space Representations [71.86401914779019]
  Physics-informed neural networks (PINNs) have made significant strides in modeling dynamical systems governed by partial differential equations (PDEs)<n>We propose PIDO, a novel physics-informed neural PDE solver designed to generalize effectively across diverse PDE configurations.<n>We validate PIDO on a range of benchmarks, including 1D combined equations and 2D Navier-Stokes equations.
  arXiv  Detail & Related papers  (2024-11-28T13:16:20Z)
• Identifying Drift, Diffusion, and Causal Structure from Temporal Snapshots [10.018568337210876]
  We present the first comprehensive approach for jointly estimating the drift and diffusion of an SDE from its temporal marginals. We show that each of these steps areAlterally optimal with respect to the Kullback-Leibler datasets.
  arXiv  Detail & Related papers  (2024-10-30T06:28:21Z)
• Trajectory Flow Matching with Applications to Clinical Time Series Modeling [77.58277281319253]
  Trajectory Flow Matching (TFM) trains a Neural SDE in a simulation-free manner, bypassing backpropagation through the dynamics.<n>We demonstrate improved performance on three clinical time series datasets in terms of absolute performance and uncertainty prediction.
  arXiv  Detail & Related papers  (2024-10-28T15:54:50Z)
• A Training-Free Conditional Diffusion Model for Learning Stochastic Dynamical Systems [10.820654486318336]
  This study introduces a training-free conditional diffusion model for learning unknown differential equations (SDEs) using data. The proposed approach addresses key challenges in computational efficiency and accuracy for modeling SDEs. The learned models exhibit significant improvements in predicting both short-term and long-term behaviors of unknown systems.
  arXiv  Detail & Related papers  (2024-10-04T03:07:36Z)
• On the Trajectory Regularity of ODE-based Diffusion Sampling [79.17334230868693]
  Diffusion-based generative models use differential equations to establish a smooth connection between a complex data distribution and a tractable prior distribution. In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models.
  arXiv  Detail & Related papers  (2024-05-18T15:59:41Z)
• Diffusion models as probabilistic neural operators for recovering unobserved states of dynamical systems [49.2319247825857]
  We show that diffusion-based generative models exhibit many properties favourable for neural operators.<n>We propose to train a single model adaptable to multiple tasks, by alternating between the tasks during training.
  arXiv  Detail & Related papers  (2024-05-11T21:23:55Z)
• Neural McKean-Vlasov Processes: Distributional Dependence in Diffusion Processes [24.24785205800212]
  McKean-Vlasov differential equations (MV-SDEs) provide a mathematical description of the behavior of an infinite number of interacting particles. We study the influence of explicitly including distributional information in the parameterization of the SDE.
  arXiv  Detail & Related papers  (2024-04-15T01:28:16Z)
• Gaussian Mixture Solvers for Diffusion Models [84.83349474361204]
  We introduce a novel class of SDE-based solvers called GMS for diffusion models. Our solver outperforms numerous SDE-based solvers in terms of sample quality in image generation and stroke-based synthesis.
  arXiv  Detail & Related papers  (2023-11-02T02:05:38Z)
• Variational Inference for SDEs Driven by Fractional Noise [16.434973057669676]
  We present a novel variational framework for performing inference in (neural) differential equations (SDEs) driven by Markov-approximate fractional Brownian motion (fBM) We propose the use of neural networks to learn the drift, diffusion and control terms within our variational posterior leading to the variational training of neural-SDEs.
  arXiv  Detail & Related papers  (2023-10-19T17:59:21Z)
• A Geometric Perspective on Diffusion Models [57.27857591493788]
  We inspect the ODE-based sampling of a popular variance-exploding SDE. We establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm.
  arXiv  Detail & Related papers  (2023-05-31T15:33:16Z)
• Score-based Diffusion Models in Function Space [137.70916238028306]
  Diffusion models have recently emerged as a powerful framework for generative modeling.<n>This work introduces a mathematically rigorous framework called Denoising Diffusion Operators (DDOs) for training diffusion models in function space.<n>We show that the corresponding discretized algorithm generates accurate samples at a fixed cost independent of the data resolution.
  arXiv  Detail & Related papers  (2023-02-14T23:50:53Z)
• A Kernel Learning Method for Backward SDE Filter [1.7035011973665108]
  We develop a kernel learning backward SDE filter method to propagate the state of a dynamical system based on its partial noisy observations. We introduce a kernel learning method to learn a continuous global approximation for the conditional probability density function of the target state. Numerical experiments demonstrate that the kernel learning backward SDE is highly effective and highly efficient.
  arXiv  Detail & Related papers  (2022-01-25T19:49:19Z)
• Stochastic Normalizing Flows [52.92110730286403]
  We introduce normalizing flows for maximum likelihood estimation and variational inference (VI) using differential equations (SDEs) Using the theory of rough paths, the underlying Brownian motion is treated as a latent variable and approximated, enabling efficient training of neural SDEs. These SDEs can be used for constructing efficient chains to sample from the underlying distribution of a given dataset.
  arXiv  Detail & Related papers  (2020-02-21T20:47:55Z)

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.