Accelerating Neural ODEs Using Model Order Reduction

• URL: http://arxiv.org/abs/2105.14070v1
• Date: Fri, 28 May 2021 19:27:09 GMT
• Title: Accelerating Neural ODEs Using Model Order Reduction
• Authors: Mikko Lehtim\"aki, Lassi Paunonen, Marja-Leena Linne
• Abstract summary: We show that mathematical model order reduction methods can be used for compressing and accelerating Neural ODEs. We implement our novel compression method by developing Neural ODEs that integrate the necessary subspace-projection and operations as layers of the neural network.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Embedding nonlinear dynamical systems into artificial neural networks is a powerful new formalism for machine learning. By parameterizing ordinary differential equations (ODEs) as neural network layers, these Neural ODEs are memory-efficient to train, process time-series naturally and incorporate knowledge of physical systems into deep learning models. However, the practical applications of Neural ODEs are limited due to long inference times, because the outputs of the embedded ODE layers are computed numerically with differential equation solvers that can be computationally demanding. Here we show that mathematical model order reduction methods can be used for compressing and accelerating Neural ODEs by accurately simulating the continuous nonlinear dynamics in low-dimensional subspaces. We implement our novel compression method by developing Neural ODEs that integrate the necessary subspace-projection and interpolation operations as layers of the neural network. We validate our model reduction approach by comparing it to two established acceleration methods from the literature in two classification asks. In compressing convolutional and recurrent Neural ODE architectures, we achieve the best balance between speed and accuracy when compared to the other two acceleration methods. Based on our results, our integration of model order reduction with Neural ODEs can facilitate efficient, dynamical system-driven deep learning in resource-constrained applications.

Related papers

• Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations [0.0]
  Variational Autoencoders (VAEs) are a powerful framework for learning compact latent representations. NeuralODEs excel in learning transient system dynamics. This work combines the strengths of both to create fast surrogate models with adjustable complexity.
  arXiv  Detail & Related papers  (2024-10-14T05:45:52Z)
• Bridging Autoencoders and Dynamic Mode Decomposition for Reduced-order Modeling and Control of PDEs [12.204795159651589]
  This paper explores a deep autocodingen learning method for reduced-order modeling and control of dynamical systems governed by Ptemporals. We first show that an objective for learning a linear autoen reduced-order model can be formulated to yield a solution closely resembling the result obtained through the dynamic mode decomposition with control algorithm. We then extend this linear autoencoding architecture to a deep autocoding framework, enabling the development of a nonlinear reduced-order model.
  arXiv  Detail & Related papers  (2024-09-09T22:56:40Z)
• Neural Fractional Differential Equations [2.812395851874055]
  Fractional Differential Equations (FDEs) are essential tools for modelling complex systems in science and engineering. We propose the Neural FDE, a novel deep neural network architecture that adjusts a FDE to the dynamics of data.
  arXiv  Detail & Related papers  (2024-03-05T07:45:29Z)
• Mechanistic Neural Networks for Scientific Machine Learning [58.99592521721158]
  We present Mechanistic Neural Networks, a neural network design for machine learning applications in the sciences. It incorporates a new Mechanistic Block in standard architectures to explicitly learn governing differential equations as representations. Central to our approach is a novel Relaxed Linear Programming solver (NeuRLP) inspired by a technique that reduces solving linear ODEs to solving linear programs.
  arXiv  Detail & Related papers  (2024-02-20T15:23:24Z)
• Correcting auto-differentiation in neural-ODE training [19.472357078065194]
  We find that when a neural network employs high-order forms to approximate the underlying ODE flows, brute-force computation using auto-differentiation often produces non-converging artificial oscillations. We propose a straightforward post-processing technique that effectively eliminates these oscillations, rectifies the computation and thus respects the updates of the underlying flow.
  arXiv  Detail & Related papers  (2023-06-03T20:34:14Z)
• Neural Delay Differential Equations: System Reconstruction and Image Classification [14.59919398960571]
  We propose a new class of continuous-depth neural networks with delay, named Neural Delay Differential Equations (NDDEs) Compared to NODEs, NDDEs have a stronger capacity of nonlinear representations. We achieve lower loss and higher accuracy not only for the data produced synthetically but also for the CIFAR10, a well-known image dataset.
  arXiv  Detail & Related papers  (2023-04-11T16:09:28Z)
• NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition [67.46012350241969]
  This paper proposes a general acceleration methodology called NeuralStagger. It decomposing the original learning tasks into several coarser-resolution subtasks. We demonstrate the successful application of NeuralStagger on 2D and 3D fluid dynamics simulations.
  arXiv  Detail & Related papers  (2023-02-20T19:36:52Z)
• Neural Laplace: Learning diverse classes of differential equations in the Laplace domain [86.52703093858631]
  We propose a unified framework for learning diverse classes of differential equations (DEs) including all the aforementioned ones. Instead of modelling the dynamics in the time domain, we model it in the Laplace domain, where the history-dependencies and discontinuities in time can be represented as summations of complex exponentials. In the experiments, Neural Laplace shows superior performance in modelling and extrapolating the trajectories of diverse classes of DEs.
  arXiv  Detail & Related papers  (2022-06-10T02:14:59Z)
• Neural Operator with Regularity Structure for Modeling Dynamics Driven by SPDEs [70.51212431290611]
  Partial differential equations (SPDEs) are significant tools for modeling dynamics in many areas including atmospheric sciences and physics. We propose the Neural Operator with Regularity Structure (NORS) which incorporates the feature vectors for modeling dynamics driven by SPDEs. We conduct experiments on various of SPDEs including the dynamic Phi41 model and the 2d Navier-Stokes equation.
  arXiv  Detail & Related papers  (2022-04-13T08:53:41Z)
• Time Dependence in Non-Autonomous Neural ODEs [74.78386661760662]
  We propose a novel family of Neural ODEs with time-varying weights. We outperform previous Neural ODE variants in both speed and representational capacity.
  arXiv  Detail & Related papers  (2020-05-05T01:41:46Z)
• Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs [71.26657499537366]
  We propose a simple literature-based method for the efficient approximation of gradients in neural ODE models. We compare it with the reverse dynamic method to train neural ODEs on classification, density estimation, and inference approximation tasks.
  arXiv  Detail & Related papers  (2020-03-11T13:15:57Z)

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.