paper-with-me

Papers

Neural Networks with Cheap Differential Operators

2019-12-01 · NeurIPS 2019 12 · Tian Qi Chen, David K. Duvenaud

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Neural Networks with Cheap Differential Operators

2019-12-08 · Ricky T. Q. Chen, David Duvenaud

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

2019-06-16 · Jordi Feliu-Faba, Yuwei Fan, Lexing Ying

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-Learning

Nonlinear integro-differential operator regression with neural networks

2018-10-19 · Ravi G. Patel, Olivier Desjardins

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…

regression

Deep Learning Solution of the Eigenvalue Problem for Differential Operators

2021-01-01 · Ido Ben-Shaul, Leah Bar, Nir Sochen

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 Learning

Data-driven discovery of free-form governing differential equations

2019-09-27 · Steven Atkinson, Waad Subber, Liping Wang, Genghis Khan 외

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