Transformers for dynamical systems learn transfer operators in-context

• URL: http://arxiv.org/abs/2602.18679v1
• Date: Sat, 21 Feb 2026 01:03:15 GMT
• Title: Transformers for dynamical systems learn transfer operators in-context
• Abstract summary: In-context learning challenges conventional understanding of learning and adaptation in physical systems.<n>We train a small two-layer, single-head transformer to forecast one dynamical system, and then evaluate its ability to forecast a different dynamical system without retraining.<n>We discover that attention-based models apply a transfer-operator forecasting strategy in-context.
• Score: 4.211463778317431
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large-scale foundation models for scientific machine learning adapt to physical settings unseen during training, such as zero-shot transfer between turbulent scales. This phenomenon, in-context learning, challenges conventional understanding of learning and adaptation in physical systems. Here, we study in-context learning of dynamical systems in a minimal setting: we train a small two-layer, single-head transformer to forecast one dynamical system, and then evaluate its ability to forecast a different dynamical system without retraining. We discover an early tradeoff in training between in-distribution and out-of-distribution performance, which manifests as a secondary double descent phenomenon. We discover that attention-based models apply a transfer-operator forecasting strategy in-context. They (1) lift low-dimensional time series using delay embedding, to detect the system's higher-dimensional dynamical manifold, and (2) identify and forecast long-lived invariant sets that characterize the global flow on this manifold. Our results clarify the mechanism enabling large pretrained models to forecast unseen physical systems at test without retraining, and they illustrate the unique ability of attention-based models to leverage global attractor information in service of short-term forecasts.

Related papers

• Interpreting learning dynamics of autoencoders: Transient scaling and emerging concepts of the Ising model [0.0]
  unsupervised autoencoders trained on microscopic spin configurations from the Ising model learn macroscopic, theory-relevant variables.<n>We quantify learning across multiple spatial scales and reveal two distinct dynamical regimes.<n>A dynamical viewpoint of learning is established in which intrinsic properties expose the effects of forced changes in representation.
  arXiv  Detail & Related papers  (2026-07-11T12:31:34Z)
• A Mechanistic Analysis of Transformers for Dynamical Systems [4.590170084532207]
  We study the representational capabilities and limitations of single-layer Transformers when applied to dynamical data.<n>For linear systems, we show that the convexity constraint imposed by softmax attention fundamentally restricts the class of dynamics that can be represented.<n>For nonlinear systems under partial observability, attention instead acts as an adaptive delay-embedding mechanism.
  arXiv  Detail & Related papers  (2025-12-24T11:21:07Z)
• Learning and Current Prediction of PMSM Drive via Differential Neural Networks [13.370017978792479]
  This study presents a novel approach utilizing differential neural networks (DNNs) to model nonlinear systems.<n>The efficacy of our approach is validated through experiments conducted under various load disturbances and no-load conditions.
  arXiv  Detail & Related papers  (2024-12-12T07:43:27Z)
• Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis [97.54180451650122]
  We study the dynamics of training a shallow transformer on a task of recognizing co-occurrence of two designated words. We analyze the gradient flow dynamics of simultaneously training three attention matrices and a linear layer. We prove a novel property of the gradient flow, termed textitautomatic balancing of gradients, which enables the loss values of different samples to decrease almost at the same rate and further facilitates the proof of near minimum training loss.
  arXiv  Detail & Related papers  (2024-10-12T17:50:58Z)
• Learning System Dynamics without Forgetting [60.08612207170659]
  We investigate the problem of Continual Dynamics Learning (CDL), examining task configurations and evaluating the applicability of existing techniques.<n>We propose the Mode-switching Graph ODE (MS-GODE) model, which integrates the strengths LG-ODE and sub-network learning with a mode-switching module.<n>We construct a novel benchmark of biological dynamic systems for CDL, Bio-CDL, featuring diverse systems with disparate dynamics.
  arXiv  Detail & Related papers  (2024-06-30T14:55:18Z)
• In-Context Convergence of Transformers [63.04956160537308]
  We study the learning dynamics of a one-layer transformer with softmax attention trained via gradient descent. For data with imbalanced features, we show that the learning dynamics take a stage-wise convergence process.
  arXiv  Detail & Related papers  (2023-10-08T17:55:33Z)
• Constraining Chaos: Enforcing dynamical invariants in the training of recurrent neural networks [0.0]
  We introduce a novel training method for machine learning based forecasting methods for chaotic dynamical systems. The training enforces dynamical invariants--such as the Lyapunov exponent spectrum and fractal dimension--in the systems of interest, enabling longer and more stable forecasts when operating with limited data.
  arXiv  Detail & Related papers  (2023-04-24T00:33:47Z)
• Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking [76.27433308688592]
  Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
  arXiv  Detail & Related papers  (2022-06-07T13:51:35Z)
• Supervised DKRC with Images for Offline System Identification [77.34726150561087]
  Modern dynamical systems are becoming increasingly non-linear and complex. There is a need for a framework to model these systems in a compact and comprehensive representation for prediction and control. Our approach learns these basis functions using a supervised learning approach.
  arXiv  Detail & Related papers  (2021-09-06T04:39:06Z)
• GEM: Group Enhanced Model for Learning Dynamical Control Systems [78.56159072162103]
  We build effective dynamical models that are amenable to sample-based learning. We show that learning the dynamics on a Lie algebra vector space is more effective than learning a direct state transition model. This work sheds light on a connection between learning of dynamics and Lie group properties, which opens doors for new research directions.
  arXiv  Detail & Related papers  (2021-04-07T01:08:18Z)
• Using Data Assimilation to Train a Hybrid Forecast System that Combines Machine-Learning and Knowledge-Based Components [52.77024349608834]
  We consider the problem of data-assisted forecasting of chaotic dynamical systems when the available data is noisy partial measurements. We show that by using partial measurements of the state of the dynamical system, we can train a machine learning model to improve predictions made by an imperfect knowledge-based model.
  arXiv  Detail & Related papers  (2021-02-15T19:56:48Z)
• Bridging Physics-based and Data-driven modeling for Learning Dynamical Systems [36.04381259949935]
  We formalize the learning of physics-based models as AutoODE, which leverages automatic differentiation to estimate the model parameters. Our method obtains a 57.4% reduction in mean absolute errors for 7-day ahead COVID-19 forecasting compared with the best deep learning competitor.
  arXiv  Detail & Related papers  (2020-11-20T20:16:10Z)

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.