Learning dynamically inspired invariant subspaces for Koopman and transfer operator approximation

• URL: http://arxiv.org/abs/2505.05085v1
• Date: Thu, 08 May 2025 09:32:39 GMT
• Title: Learning dynamically inspired invariant subspaces for Koopman and transfer operator approximation
• Authors: Gary Froyland, Kevin Kühl,
• Abstract summary: Transfer and Koopman operator methods offer a framework for representing complex, nonlinear dynamical systems via linear transformations.<n>We tackle this issue through the lens of general operator and representational learning, in which we approximate these linear operators using efficient finite-dimensional representations.<n>Specifically, we machine-learn orthonormal, locally supported basis functions that are dynamically tailored to the system.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transfer and Koopman operator methods offer a framework for representing complex, nonlinear dynamical systems via linear transformations, enabling for a deeper understanding of the underlying dynamics. The spectrum of these operators provide important insights into system predictability and emergent behaviour, although efficiently estimating them from data can be challenging. We tackle this issue through the lens of general operator and representational learning, in which we approximate these linear operators using efficient finite-dimensional representations. Specifically, we machine-learn orthonormal, locally supported basis functions that are dynamically tailored to the system. This learned basis provides a particularly accurate approximation of the operator's action as well as a nearly invariant finite-dimensional subspace. We illustrate our approach with examples that showcase the retrieval of spectral properties from the estimated operator, and emphasise the dynamically adaptive quality of the machine-learned basis.

Related papers

• Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems [35.207148596300684]
  The Koopman operator provides a principled framework for analyzing nonlinear dynamical systems.<n>VAMPnet and DPNet have been proposed to learn the leading singular subspaces of the Koopman operator.<n>We propose a scalable and conceptually simple method for learning the top-k singular functions of the Koopman operator.
  arXiv  Detail & Related papers  (2025-07-09T18:55:48Z)
• Nonparametric Sparse Online Learning of the Koopman Operator [11.710740395697128]
  The Koopman operator provides a powerful framework for representing the dynamics of general nonlinear dynamical systems.<n>Data-driven techniques to learn the Koopman operator typically assume that the chosen function space is closed under system dynamics.<n>We present an operator approximation algorithm to learn the Koopman operator iteratively with control over the complexity of the representation.
  arXiv  Detail & Related papers  (2025-01-27T20:48:10Z)
• Interpreting Affine Recurrence Learning in GPT-style Transformers [54.01174470722201]
  In-context learning allows GPT-style transformers to generalize during inference without modifying their weights. This paper focuses specifically on their ability to learn and predict affine recurrences as an ICL task. We analyze the model's internal operations using both empirical and theoretical approaches.
  arXiv  Detail & Related papers  (2024-10-22T21:30:01Z)
• Strengthening Structural Inductive Biases by Pre-training to Perform Syntactic Transformations [75.14793516745374]
  We propose to strengthen the structural inductive bias of a Transformer by intermediate pre-training. Our experiments confirm that this helps with few-shot learning of syntactic tasks such as chunking. Our analysis shows that the intermediate pre-training leads to attention heads that keep track of which syntactic transformation needs to be applied to which token.
  arXiv  Detail & Related papers  (2024-07-05T14:29:44Z)
• Nonparametric Sparse Online Learning of the Koopman Operator [11.710740395697128]
  The Koopman operator provides a powerful framework for representing the dynamics of general nonlinear dynamical systems.<n>Data-driven techniques to learn the Koopman operator typically assume that the chosen function space is closed under system dynamics.<n>We present an operator approximation algorithm to learn the Koopman operator iteratively with control over the complexity of the representation.
  arXiv  Detail & Related papers  (2024-05-13T02:18:49Z)
• Multiplicative Dynamic Mode Decomposition [4.028503203417233]
  We introduce Multiplicative Dynamic Mode Decomposition (MultDMD), which enforces the multiplicative structure inherent in the Koopman operator within its finite-dimensional approximation.<n>MultDMD presents a structured approach to finite-dimensional approximations and can accurately reflect the spectral properties of the Koopman operator.<n>We elaborate on the theoretical framework of MultDMD, detailing its formulation, optimization strategy, and convergence properties.
  arXiv  Detail & Related papers  (2024-05-08T18:09:16Z)
• Online Estimation of the Koopman Operator Using Fourier Features [9.422860826278788]
  We offer an optimization scheme to allow joint learning of the observables and Koopman operator with online data. Our results show we are able to reconstruct the evolution and represent the global features of complex dynamical systems.
  arXiv  Detail & Related papers  (2022-12-03T01:39:05Z)
• Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency [111.83670279016599]
  We study reinforcement learning for partially observed decision processes (POMDPs) with infinite observation and state spaces. We make the first attempt at partial observability and function approximation for a class of POMDPs with a linear structure.
  arXiv  Detail & Related papers  (2022-04-20T21:15:38Z)
• Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization [76.68866368409216]
  We propose learning to dynamically select discretization tightness conditioned on inputs. We show that dynamically varying tightness in communication bottlenecks can improve model performance on visual reasoning and reinforcement learning tasks.
  arXiv  Detail & Related papers  (2022-02-02T23:54:26Z)
• 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)
• Estimating Koopman operators for nonlinear dynamical systems: a nonparametric approach [77.77696851397539]
  The Koopman operator is a mathematical tool that allows for a linear description of non-linear systems. In this paper we capture their core essence as a dual version of the same framework, incorporating them into the Kernel framework. We establish a strong link between kernel methods and Koopman operators, leading to the estimation of the latter through Kernel functions.
  arXiv  Detail & Related papers  (2021-03-25T11:08:26Z)
• Functional Space Analysis of Local GAN Convergence [26.985600125290908]
  We study the local dynamics of adversarial training in the general functional space. We show how it can be represented as a system of partial differential equations. Our perspective reveals several insights on the practical tricks commonly used to stabilize GANs.
  arXiv  Detail & Related papers  (2021-02-08T18:59:46Z)

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.