Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional Distributions

• URL: http://arxiv.org/abs/2410.03973v1
• Date: Fri, 4 Oct 2024 23:26:38 GMT
• Title: Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional Distributions
• Authors: Jianxin Zhang, Josh Viktorov, Doosan Jung, Emily Pitler,
• Abstract summary: We develop a novel scoring rule for comparing continuous Markov processes. This scoring rule allows us to bypass the computational overhead associated with signature kernels. We demonstrate that FDM achieves superior performance, consistently outperforming existing methods in terms of both computational efficiency and generative quality.
• Score: 3.889230974713832
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural Stochastic Differential Equations (Neural SDEs) have emerged as powerful mesh-free generative models for continuous stochastic processes, with critical applications in fields such as finance, physics, and biology. Previous state-of-the-art methods have relied on adversarial training, such as GANs, or on minimizing distance measures between processes using signature kernels. However, GANs suffer from issues like instability, mode collapse, and the need for specialized training techniques, while signature kernel-based methods require solving linear PDEs and backpropagating gradients through the solver, whose computational complexity scales quadratically with the discretization steps. In this paper, we identify a novel class of strictly proper scoring rules for comparing continuous Markov processes. This theoretical finding naturally leads to a novel approach called Finite Dimensional Matching (FDM) for training Neural SDEs. Our method leverages the Markov property of SDEs to provide a computationally efficient training objective. This scoring rule allows us to bypass the computational overhead associated with signature kernels and reduces the training complexity from $O(D^2)$ to $O(D)$ per epoch, where $D$ represents the number of discretization steps of the process. We demonstrate that FDM achieves superior performance, consistently outperforming existing methods in terms of both computational efficiency and generative quality.

Related papers

• A Simulation-Free Deep Learning Approach to Stochastic Optimal Control [12.699529713351287]
  We propose a simulation-free algorithm for the solution of generic problems in optimal control (SOC) Unlike existing methods, our approach does not require the solution of an adjoint problem.
  arXiv  Detail & Related papers  (2024-10-07T16:16:53Z)
• Partial-differential-algebraic equations of nonlinear dynamics by Physics-Informed Neural-Network: (I) Operator splitting and framework assessment [51.3422222472898]
  Several forms for constructing novel physics-informed-networks (PINN) for the solution of partial-differential-algebraic equations are proposed. Among these novel methods are the PDE forms, which evolve from the lower-level form with fewer unknown dependent variables to higher-level form with more dependent variables.
  arXiv  Detail & Related papers  (2024-07-13T22:48:17Z)
• Non-adversarial training of Neural SDEs with signature kernel scores [4.721845865189578]
  State-of-the-art performance for irregular time series generation has been previously obtained by training these models adversarially as GANs. In this paper, we introduce a novel class of scoring rules on pathspace based on signature kernels.
  arXiv  Detail & Related papers  (2023-05-25T17:31:18Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation [59.45669299295436]
  We propose a Monte Carlo PDE solver for training unsupervised neural solvers. We use the PDEs' probabilistic representation, which regards macroscopic phenomena as ensembles of random particles. Our experiments on convection-diffusion, Allen-Cahn, and Navier-Stokes equations demonstrate significant improvements in accuracy and efficiency.
  arXiv  Detail & Related papers  (2023-02-10T08:05:19Z)
• Learnable Path in Neural Controlled Differential Equations [11.38331901271794]
  Neural controlled differential equations (NCDEs) are a specialized model in (irregular) time-series processing. We present a method to generate another latent path, which is identical to learning an appropriate method. We design an encoder-decoder module based on NCDEs and NODEs, and a special training method for it.
  arXiv  Detail & Related papers  (2023-01-11T07:05:27Z)
• JAX-DIPS: Neural bootstrapping of finite discretization methods and application to elliptic problems with discontinuities [0.0]
  This strategy can be used to efficiently train neural network surrogate models of partial differential equations. The presented neural bootstrapping method (hereby dubbed NBM) is based on evaluation of the finite discretization residuals of the PDE system. We show NBM is competitive in terms of memory and training speed with other PINN-type frameworks.
  arXiv  Detail & Related papers  (2022-10-25T20:13:26Z)
• Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations [57.15855198512551]
  We propose a novel score-based generative model for graphs with a continuous-time framework. We show that our method is able to generate molecules that lie close to the training distribution yet do not violate the chemical valency rule.
  arXiv  Detail & Related papers  (2022-02-05T08:21:04Z)
• Large-scale Neural Solvers for Partial Differential Equations [48.7576911714538]
  Solving partial differential equations (PDE) is an indispensable part of many branches of science as many processes can be modelled in terms of PDEs. Recent numerical solvers require manual discretization of the underlying equation as well as sophisticated, tailored code for distributed computing. We examine the applicability of continuous, mesh-free neural solvers for partial differential equations, physics-informed neural networks (PINNs) We discuss the accuracy of GatedPINN with respect to analytical solutions -- as well as state-of-the-art numerical solvers, such as spectral solvers.
  arXiv  Detail & Related papers  (2020-09-08T13:26:51Z)
• Efficient Learning of Generative Models via Finite-Difference Score Matching [111.55998083406134]
  We present a generic strategy to efficiently approximate any-order directional derivative with finite difference. Our approximation only involves function evaluations, which can be executed in parallel, and no gradient computations.
  arXiv  Detail & Related papers  (2020-07-07T10:05:01Z)
• Weak SINDy For Partial Differential Equations [0.0]
  We extend our Weak SINDy (WSINDy) framework to the setting of partial differential equations (PDEs) The elimination of pointwise derivative approximations via the weak form enables effective machine-precision recovery of model coefficients from noise-free data. We demonstrate WSINDy's robustness, speed and accuracy on several challenging PDEs.
  arXiv  Detail & Related papers  (2020-07-06T16:03:51Z)

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.