paper-with-me

Papers

A Constructive Approach to Function Realization by Neural Stochastic Differential Equations

2023-07-01 · Tanya Veeravalli, Maxim Raginsky

The problem of function approximation by neural dynamical systems has typically been approached in a top-down manner: Any continuous function can be approximated to an arbitrary accuracy by a sufficiently complex model with a given architecture. This can lead to high-complexity controls which are impractical in applications. In this paper, we take the opposite, constructive approach: We impose various structural restrictions on system dynamics and consequently characterize the class of functions that can be realized by such a system. The systems are implemented as a cascade interconnection of a neural stochastic differential equation (Neural SDE), a deterministic dynamical system, and a readout map. Both probabilistic and geometric (Lie-theoretic) methods are used to characterize the classes of functions realized by such systems.

📄 PDF Abstract BibTeX arXiv:2307.00215

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Deep learning based numerical approximation algorithms for stochastic partial differential equations and high-dimensional nonlinear filtering problems

2020-12-02 · Christian Beck, Sebastian Becker, Patrick Cheridito, Arnulf Jentzen 외

In this article we introduce and study a deep learning based approximation algorithm for solutions of stochastic partial differential equations (SPDEs). In the proposed approximation algorithm we employ a deep neural net…

Physics-Information-Aided Kriging: Constructing Covariance Functions using Stochastic Simulation Models

2018-09-10 · Xiu Yang, Guzel Tartakovsky, Alexandre Tartakovsky

In this work, we propose a new Gaussian process regression (GPR) method: physics information aided Kriging (PhIK). In the standard data-driven Kriging, the unknown function of interest is usually treated as a Gaussian pr…

Active LearningGPR

Forward-Backward Stochastic Neural Networks: Deep Learning of High-dimensional Partial Differential Equations

2018-04-19 · Maziar Raissi

Classical numerical methods for solving partial differential equations suffer from the curse dimensionality mainly due to their reliance on meticulously generated spatio-temporal grids. Inspired by modern deep learning b…

Probabilistic learning on manifolds constrained by nonlinear partial differential equations for small datasets

2020-10-27 · Christian Soize, Roger Ghanem

A novel extension of the Probabilistic Learning on Manifolds (PLoM) is presented. It makes it possible to synthesize solutions to a wide range of nonlinear stochastic boundary value problems described by partial differen…

Neural Ideal Large Eddy Simulation: Modeling Turbulence with Neural Stochastic Differential Equations

2023-06-01 · NeurIPS 2023 11

We introduce a data-driven learning framework that assimilates two powerful ideas: ideal large eddy simulation (LES) from turbulence closure modeling and neural stochastic differential equations (SDE) for stochastic mode…

Decoder