DeepAI AI Chat
Log In Sign Up

Scalable Gradients for Stochastic Differential Equations

01/05/2020
by   Xuechen Li, et al.
19

The adjoint sensitivity method scalably computes gradients of solutions to ordinary differential equations. We generalize this method to stochastic differential equations, allowing time-efficient and constant-memory computation of gradients with high-order adaptive solvers. Specifically, we derive a stochastic differential equation whose solution is the gradient, a memory-efficient algorithm for caching noise, and conditions under which numerical solutions converge. In addition, we combine our method with gradient-based stochastic variational inference for latent stochastic differential equations. We use our method to fit stochastic dynamics defined by neural networks, achieving competitive performance on a 50-dimensional motion capture dataset.

READ FULL TEXT
02/12/2021

Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations

We perform scalable approximate inference in a recently-proposed family ...
11/17/2022

Neural Langevin Dynamics: towards interpretable Neural Stochastic Differential Equations

Neural Stochastic Differential Equations (NSDE) have been trained as bot...
05/17/2021

Adaptive Density Tracking by Quadrature for Stochastic Differential Equations

Density tracking by quadrature (DTQ) is a numerical procedure for comput...
03/23/2018

From Random Differential Equations to Structural Causal Models: the stochastic case

Random Differential Equations provide a natural extension of Ordinary Di...
09/14/2022

Vectorized Adjoint Sensitivity Method for Graph Convolutional Neural Ordinary Differential Equations

This document, as the title stated, is meant to provide a vectorized imp...
06/16/2021

Fréchet derivatives of expected functionals of solutions to stochastic differential equations

In the analysis of stochastic dynamical systems described by stochastic ...
05/19/2017

Scalable Variational Inference for Dynamical Systems

Gradient matching is a promising tool for learning parameters and state ...

Code Repositories

torchsde

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.


view repo

bayesian-sde

Code for "Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations"


view repo