Scaling Law of Neural Koopman Operators

• URL: http://arxiv.org/abs/2602.19943v1
• Date: Mon, 23 Feb 2026 15:13:43 GMT
• Title: Scaling Law of Neural Koopman Operators
• Abstract summary: Data-driven neural Koopman operator theory has emerged as a powerful tool for linearizing and controlling nonlinear robotic systems.<n>This paper establishes a rigorous framework to address this challenge by deriving and empirically validating scaling laws.<n>We show that these terms decay at specific rates relative to dataset size and latent dimension, providing a rigorous basis for the scaling law.
• Score: 9.640698542980179
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data-driven neural Koopman operator theory has emerged as a powerful tool for linearizing and controlling nonlinear robotic systems. However, the performance of these data-driven models fundamentally depends on the trade-off between sample size and model dimensions, a relationship for which the scaling laws have remained unclear. This paper establishes a rigorous framework to address this challenge by deriving and empirically validating scaling laws that connect sample size, latent space dimension, and downstream control quality. We derive a theoretical upper bound on the Koopman approximation error, explicitly decomposing it into sampling error and projection error. We show that these terms decay at specific rates relative to dataset size and latent dimension, providing a rigorous basis for the scaling law. Based on the theoretical results, we introduce two lightweight regularizers for the neural Koopman operator: a covariance loss to help stabilize the learned latent features and an inverse control loss to ensure the model aligns with physical actuation. The results from systematic experiments across six robotic environments confirm that model fitting error follows the derived scaling laws, and the regularizers improve dynamic model fitting fidelity, with enhanced closed-loop control performance. Together, our results provide a simple recipe for allocating effort between data collection and model capacity when learning Koopman dynamics for control.

Related papers

• Neural Scaling Laws for Jet Generation [0.46843765915430247]
  This work explores if scaling laws can also be observed for the task of particle jet generation.<n>We study the sliced Wasserstein distance of five physical quantities that are not immediately available to the model during training.<n>For the scaling with dataset size and compute, we observe substantially weaker scaling behavior of both the loss and the sliced Wasserstein distance.
  arXiv  Detail & Related papers  (2026-05-27T18:00:03Z)
• Adaptive Learning via Off-Model Training and Importance Sampling for Fully Non-Markovian Optimal Stochastic Control. Complete version [0.0]
  This paper studies continuous-time control problems whose controlled states are fully non-Markovian and depend on unknown model parameters.<n>Building on the discrete skeleton approach developed in earlier work, we propose a Monte Carlo learning methodology for the embedded backward dynamic programming equation.
  arXiv  Detail & Related papers  (2026-04-14T16:32:46Z)
• Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors [60.06461883533697]
  We leverage rank-one model editing to establish an attribution-guided model rectification framework.<n>We first distinguish our rectification setting from existing model editing, yielding a formulation that corrects unreliable behavior.<n>To target the primary source of misbehavior, we introduce an attribution-guided layer localization method.
  arXiv  Detail & Related papers  (2026-03-08T01:06:07Z)
• Solving and learning advective multiscale Darcian dynamics with the Neural Basis Method [4.331539387944184]
  We introduce the Neural Basis Method, a projection-based formulation that couples a physics-conforming neural basis space with an operator-induced residual metric.<n>Our method produce accurate and robust solutions in single solves and enable fast and effective parametric inference with operator learning.
  arXiv  Detail & Related papers  (2026-02-19T19:17:55Z)
• Hybrid twinning using PBDW and DeepONet for the effective state estimation and prediction on partially known systems [0.0]
  We propose an effective hybrid approach that combines physics-based modeling with data-driven learning to enhance state estimation.<n>We validate the proposed approach on a representative problem involving the Helmholtz equation.
  arXiv  Detail & Related papers  (2025-12-03T12:19:00Z)
• Nonparametric Data Attribution for Diffusion Models [57.820618036556084]
  Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs.<n>We propose a nonparametric attribution method that operates entirely on data, measuring influence via patch-level similarity between generated and training images.
  arXiv  Detail & Related papers  (2025-10-16T03:37:16Z)
• Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks [59.552873049024775]
  We show that compute-optimally trained models exhibit a remarkably precise universality.<n>With learning rate decay, the collapse becomes so tight that differences in the normalized curves across models fall below the noise floor.<n>We explain these phenomena by connecting collapse to the power-law structure in typical neural scaling laws.
  arXiv  Detail & Related papers  (2025-07-02T20:03:34Z)
• Imitation Learning of MPC with Neural Networks: Error Guarantees and Sparsification [5.260346080244568]
  We present a framework for bounding the approximation error in imitation model predictive controllers utilizing neural networks.<n>We discuss how this method can be used to design a stable neural network controller with performance guarantees.
  arXiv  Detail & Related papers  (2025-01-07T10:18:37Z)
• Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence [19.484676783876306]
  Diffusion models have emerged as powerful tools for generative modeling.<n>We propose a control framework for fine-tuning diffusion models.<n>We show that PI-FT achieves global convergence at a linear rate.
  arXiv  Detail & Related papers  (2024-12-24T04:55:46Z)
• Data-driven Nonlinear Model Reduction using Koopman Theory: Integrated Control Form and NMPC Case Study [56.283944756315066]
  We propose generic model structures combining delay-coordinate encoding of measurements and full-state decoding to integrate reduced Koopman modeling and state estimation. A case study demonstrates that our approach provides accurate control models and enables real-time capable nonlinear model predictive control of a high-purity cryogenic distillation column.
  arXiv  Detail & Related papers  (2024-01-09T11:54:54Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• A Solvable Model of Neural Scaling Laws [72.8349503901712]
  Large language models with a huge number of parameters, when trained on near internet-sized number of tokens, have been empirically shown to obey neural scaling laws. We propose a statistical model -- a joint generative data model and random feature model -- that captures this neural scaling phenomenology. Key findings are the manner in which the power laws that occur in the statistics of natural datasets are extended by nonlinear random feature maps.
  arXiv  Detail & Related papers  (2022-10-30T15:13:18Z)
• Derivative-Based Koopman Operators for Real-Time Control of Robotic Systems [14.211417879279075]
  This paper presents a generalizable methodology for data-driven identification of nonlinear dynamics that bounds the model error. We construct a Koopman operator-based linear representation and utilize Taylor series accuracy analysis to derive an error bound. When combined with control, the Koopman representation of the nonlinear system has marginally better performance than competing nonlinear modeling methods.
  arXiv  Detail & Related papers  (2020-10-12T15:15:13Z)

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.