Neural Langevin Dynamics: towards interpretable Neural Stochastic Differential Equations

11/17/2022
by   Simon M. Koop, et al.
0

Neural Stochastic Differential Equations (NSDE) have been trained as both Variational Autoencoders, and as GANs. However, the resulting Stochastic Differential Equations can be hard to interpret or analyse due to the generic nature of the drift and diffusion fields. By restricting our NSDE to be of the form of Langevin dynamics, and training it as a VAE, we obtain NSDEs that lend themselves to more elaborate analysis and to a wider range of visualisation techniques than a generic NSDE. More specifically, we obtain an energy landscape, the minima of which are in one-to-one correspondence with latent states underlying the used data. This not only allows us to detect states underlying the data dynamics in an unsupervised manner, but also to infer the distribution of time spent in each state according to the learned SDE. More in general, restricting an NSDE to Langevin dynamics enables the use of a large set of tools from computational molecular dynamics for the analysis of the obtained results.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/05/2020

Scalable Gradients for Stochastic Differential Equations

The adjoint sensitivity method scalably computes gradients of solutions ...
research
06/10/2023

How to Learn and Generalize From Three Minutes of Data: Physics-Constrained and Uncertainty-Aware Neural Stochastic Differential Equations

We present a framework and algorithms to learn controlled dynamics model...
research
05/04/2022

Learning Individual Interactions from Population Dynamics with Discrete-Event Simulation Model

The abundance of data affords researchers to pursue more powerful comput...
research
06/11/2020

Learning Continuous-Time Dynamics by Stochastic Differential Networks

Learning continuous-time stochastic dynamics from sparse or irregular ob...
research
02/23/2021

Inferring temporal dynamics from cross-sectional data using Langevin dynamics

Cross-sectional studies are widely prevalent since they are more feasibl...
research
07/12/2020

Learning latent stochastic differential equations with variational auto-encoders

We present a method for learning latent stochastic differential equation...
research
10/11/2021

Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations

Understanding the training dynamics of deep learning models is perhaps a...

Please sign up or login with your details

Forgot password? Click here to reset