mlsanityData to 7 Oct 2026

Neural Langevin Dynamics: towards interpretable Neural Stochastic Differential Equations

arXiv 2211.09537 ↗First posted 17 Nov 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 38 references that are in the map. First posted on arXiv 17 Nov 2022.

Builds on

20 of 38 references.

References · 20

  1. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2019Hamiltonian Neural Networkscited by 702
  4. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 501
  5. 2020Lagrangian Neural Networkscited by 388
  6. 2017How to Escape Saddle Points Efficientlycited by 284
  7. 2020Scalable Gradients for Stochastic Differential Equationscited by 264
  8. 2019Latent ODEs for Irregularly-Sampled Time Seriescited by 182
  9. 2019Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limitcited by 168
  10. 2021Neural SDEs as Infinite-Dimensional GANscited by 159
  11. 2019Hamiltonian Generative Networkscited by 136
  12. 2021Efficient and Accurate Gradients for Neural SDEscited by 68
8 more
  1. 2021Sig-Wasserstein GANs for Time Series Generationcited by 60
  2. 2021Learning effective stochastic differential equations from microscopic simulations: linking stochastic numerics to deep learningcited by 37
  3. 2019ODE2VAE: Deep generative second order ODEs with Bayesian neural networkscited by 36
  4. 2021Which priors matter? Benchmarking models for learning latent dynamicscited by 26
  5. 2019Infinitely deep neural networks as diffusion processescited by 21
  6. 2020Identifying Latent Stochastic Differential Equationscited by 21
  7. 2021Escape saddle points by a simple gradient-descent based algorithmcited by 11
  8. 2021Robust and Scalable SDE Learning: A Functional Perspectivecited by 3

Built on by

Not cited yet.