Markov Neural Operators for Learning Chaotic Systems

• URL: http://arxiv.org/abs/2106.06898v1
• Date: Sun, 13 Jun 2021 02:24:50 GMT
• Title: Markov Neural Operators for Learning Chaotic Systems
• Authors: Zongyi Li, Nikola Kovachki, Kamyar Azizzadenesheli, Burigede Liu, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar
• Abstract summary: Chaotic systems are notoriously challenging to predict because of their instability. We train a Markov neural operator with only the local one-step evolution information. We then compose the learned operator to obtain the global attractor and invariant measure.
• Score: 40.256994804214315
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Chaotic systems are notoriously challenging to predict because of their instability. Small errors accumulate in the simulation of each time step, resulting in completely different trajectories. However, the trajectories of many prominent chaotic systems live in a low-dimensional subspace (attractor). If the system is Markovian, the attractor is uniquely determined by the Markov operator that maps the evolution of infinitesimal time steps. This makes it possible to predict the behavior of the chaotic system by learning the Markov operator even if we cannot predict the exact trajectory. Recently, a new framework for learning resolution-invariant solution operators for PDEs was proposed, known as neural operators. In this work, we train a Markov neural operator (MNO) with only the local one-step evolution information. We then compose the learned operator to obtain the global attractor and invariant measure. Such a Markov neural operator forms a discrete semigroup and we empirically observe that does not collapse or blow up. Experiments show neural operators are more accurate and stable compared to previous methods on chaotic systems such as the Kuramoto-Sivashinsky and Navier-Stokes equations.

Related papers

• Banach neural operator for Navier-Stokes equations [3.3864304526742397]
  We introduce Banach neural operator (BNO) -- a novel framework that integrates Koopman operator theory with deep neural networks to predict nonlinear,temporal dynamics from partial observations.<n>BNO approximates a nonlinear operator between Banach spaces by combining spectral linearization with deep feature learning (via convolutional neural networks and nonlinear activations)<n> Numerical experiments on the NavierStoke-sequences equations demonstrate the method's accuracy and generalization capabilities.
  arXiv  Detail & Related papers  (2025-11-28T21:07:41Z)
• Operator Learning at Machine Precision [36.02387239941959]
  We introduce CHONKNORIS (Cholesky Newton--Kantorovich Neural Operator Residual Iterative System), an operator learning paradigm that can achieve machine precision.<n>ChoNKNORIS draws on numerical analysis: many nonlinear forward and inverse PDE problems are solvable by Newton-type methods.<n>Our model is able to accurately solve unseen nonlinear PDEs such as the Klein--Gordon and Sine--Gordon equations.
  arXiv  Detail & Related papers  (2025-11-25T06:49:25Z)
• BlinDNO: A Distributional Neural Operator for Dynamical System Reconstruction from Time-Label-Free data [6.810595986800653]
  We study an inverse problem for quantum dynamical systems in a time-label-free setting.<n>We propose BlinDNO, a permutation-invariant architecture that integrates a multiscale U-Net encoder with an attention-based mixer.
  arXiv  Detail & Related papers  (2025-11-15T18:15:37Z)
• Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems [51.54065545849027]
  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)
• Using Machine Learning and Neural Networks to Analyze and Predict Chaos in Multi-Pendulum and Chaotic Systems [0.24548437381817975]
  Chaotic systems are prevalent throughout the world today: in weather patterns, disease outbreaks, and even financial markets.<n>We evaluate 10 different machine learning models and neural networks for their ability to predict one of these systems, the multi-pendulum.
  arXiv  Detail & Related papers  (2025-04-18T04:12:14Z)
• Neural Operators for Predictor Feedback Control of Nonlinear Delay Systems [3.0248879829045388]
  We introduce a new perspective on predictor designs by recasting the predictor formulation as an operator learning problem. We prove the existence of an arbitrarily accurate neural operator approximation of the predictor operator. Under the approximated-predictor, we achieve semiglobal practical stability of the closed-loop nonlinear system.
  arXiv  Detail & Related papers  (2024-11-28T07:30:26Z)
• Linearization Turns Neural Operators into Function-Valued Gaussian Processes [23.85470417458593]
  We introduce a new framework for approximate Bayesian uncertainty quantification in neural operators. Our approach can be interpreted as a probabilistic analogue of the concept of currying from functional programming. We showcase the efficacy of our approach through applications to different types of partial differential equations.
  arXiv  Detail & Related papers  (2024-06-07T16:43:54Z)
• Neural Operators with Localized Integral and Differential Kernels [77.76991758980003]
  We present a principled approach to operator learning that can capture local features under two frameworks. We prove that we obtain differential operators under an appropriate scaling of the kernel values of CNNs. To obtain local integral operators, we utilize suitable basis representations for the kernels based on discrete-continuous convolutions.
  arXiv  Detail & Related papers  (2024-02-26T18:59:31Z)
• Learning-based Design of Luenberger Observers for Autonomous Nonlinear Systems [5.953597709282766]
  Luenberger observers for nonlinear systems involve transforming the state to an alternate coordinate system. We propose a novel approach that uses supervised physics-informed neural networks to approximate both the transformation and its inverse. Our method exhibits superior robustness capabilities to contemporary methods and demonstrates to both neural network's approximation errors and system uncertainties.
  arXiv  Detail & Related papers  (2022-10-04T09:03:43Z)
• Approximate Bayesian Neural Operators: Uncertainty Quantification for Parametric PDEs [34.179984253109346]
  We provide a mathematically detailed Bayesian formulation of the ''shallow'' (linear) version of neural operators. We then extend this analytic treatment to general deep neural operators using approximate methods from Bayesian deep learning. As a result, our approach is able to identify cases, and provide structured uncertainty estimates, where the neural operator fails to predict well.
  arXiv  Detail & Related papers  (2022-08-02T16:10:27Z)
• Physics-Informed Neural Operators [3.9181541460605116]
  Neural networks can approximate general nonlinear operators, represented either explicitly by a combination of mathematical operators, e.g., in an advection-diffusion-reaction partial differential equation. The first neural operator was the Deep Operator Network (DeepONet), proposed in 2019 based on rigorous approximation theory. For black box systems, training of neural operators is data-driven only but if the governing equations are known they can be incorporated into the loss function during training to develop physics-informed neural operators.
  arXiv  Detail & Related papers  (2022-07-08T12:29:09Z)
• Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces [52.35063796758121]
  We formalize a framework to learn the Koopman operator from finite data trajectories of the dynamical system. We link the risk with the estimation of the spectral decomposition of the Koopman operator. Our results suggest RRR might be beneficial over other widely used estimators.
  arXiv  Detail & Related papers  (2022-05-27T14:57:48Z)
• Characterizing possible failure modes in physics-informed neural networks [55.83255669840384]
  Recent work in scientific machine learning has developed so-called physics-informed neural network (PINN) models. We demonstrate that, while existing PINN methodologies can learn good models for relatively trivial problems, they can easily fail to learn relevant physical phenomena even for simple PDEs. We show that these possible failure modes are not due to the lack of expressivity in the NN architecture, but that the PINN's setup makes the loss landscape very hard to optimize.
  arXiv  Detail & Related papers  (2021-09-02T16:06:45Z)
• Neural Operator: Learning Maps Between Function Spaces [75.93843876663128]
  We propose a generalization of neural networks to learn operators, termed neural operators, that map between infinite dimensional function spaces. We prove a universal approximation theorem for our proposed neural operator, showing that it can approximate any given nonlinear continuous operator. An important application for neural operators is learning surrogate maps for the solution operators of partial differential equations.
  arXiv  Detail & Related papers  (2021-08-19T03:56:49Z)
• Fourier Neural Operator for Parametric Partial Differential Equations [57.90284928158383]
  We formulate a new neural operator by parameterizing the integral kernel directly in Fourier space. We perform experiments on Burgers' equation, Darcy flow, and Navier-Stokes equation. It is up to three orders of magnitude faster compared to traditional PDE solvers.
  arXiv  Detail & Related papers  (2020-10-18T00:34:21Z)

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.