Skip to content

Assessment of Intrinsic Dimension (ID) algorithms for dynamical systems phase space dimension estimation

Notifications You must be signed in to change notification settings

fchavelli/id-estimation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

ID Estimation

Comparison of the following intrinsic dimension (ID) estimators:

- Grassberger and Procaccia's Correlation Integral (CorrInt)
- Farahmand et al.'s Manifold-Adaptive Dimension estimation Algorithm (MADA)
- Levina and Bickel's and Haro et al.'s maximum likelihood-based estimators (Levina_Bickel and MLE)
- Rozza et al.'s Minimum Neighbour Distance-Maximum Likelihood estimators (MiND_ML)
- Facco et al.'s Two-Nearest Neighbour estimator (TwoNN)
- Amsaleg et al.'s method of moments estimator (MOM)
- Hein and Audibert's U-statistic-based estimator (Hein)

The ID estimates are performed on the latent representations of dynamical systems obtained using the model from Chen et al. here

About

Assessment of Intrinsic Dimension (ID) algorithms for dynamical systems phase space dimension estimation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published