Neural Networks with Cheap Differential Operators
Gradients of neural networks can be computed efficiently for any architecture, but some applications require computing differential operators with higher time complexity. We describe a family of neural network architectures that allow easy access to a family of differential operators involving \emph{dimension-wise derivatives}, and we show how to modify the backward computation graph to compute them efficiently. We demonstrate the use of these operators for solving root-finding subproblems in implicit ODE solvers, exact density evaluation for continuous normalizing flows, and evaluating the Fokker-Planck equation for training stochastic differential equation models.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Neural Networks with Cheap Differential Operators
Gradients of neural networks can be computed efficiently for any architecture, but some applications require differential operators with higher time complexity. We describe a family of restricted neural network architect…
Meta-learning Pseudo-differential Operators with Deep Neural Networks
This paper introduces a meta-learning approach for parameterized pseudo-differential operators with deep neural networks. With the help of the nonstandard wavelet form, the pseudo-differential operators can be approximat…
FormMeta-LearningNonlinear integro-differential operator regression with neural networks
This note introduces a regression technique for finding a class of nonlinear integro-differential operators from data. The method parametrizes the spatial operator with neural networks and Fourier transforms such that it…
regressionDeep Learning Solution of the Eigenvalue Problem for Differential Operators
Solving the eigenvalue problem for differential operators is a common problem in many scientific fields. Classical numerical methods rely on intricate domain discretization, and yield non-analytic or non-smooth approxima…
Deep LearningData-driven discovery of free-form governing differential equations
We present a method of discovering governing differential equations from data without the need to specify a priori the terms to appear in the equation. The input to our method is a dataset (or ensemble of datasets) corre…
Active LearningForm