Kristian Agasøster Haaga

Results 104 issues of Kristian Agasøster Haaga

The user needs a quick way of visually verifying that the fitted distribution actually fits the data. Just create a plot recipe for `FittedDistribution`, where separate histograms for the empirical...

[Gao et al.](https://ieeexplore.ieee.org/abstract/document/8294268?casa_token=mhPh_2dCtD8AAAAA:gwiAJxyZ3NBmDKenRa-tA-IinCyLE8ZBOkV9G8V30LldEK7TkkTQcBWpXxXMjqqogVrFlMPm2Q) define estimators of multi-information (i.e. mutual information for more than two variables) analogous to the KSG and BI-KSG estimators. We should implement these here. This requires defining...

api
new estimator
feature request

We should add the following recent paper to the references for `TERenyiJizba`. https://www.mdpi.com/1099-4300/24/7/855. They give a more detailed treatment than Jizba et al. (2012).

documentation

I haven't read the paper yet, but this is potentially something to implement: Yamashita Rios de Sousa, A. M., & Hlinka, J. (2023). Sign patterns symbolization and its use in...

new algorithm
feature request

This is just a minor modification in the lower-level `predict` function.

enhancement
feature request

From [Lungarella, Max, Alex Pitti, and Yasuo Kuniyoshi. "Information transfer at multiple scales." Physical Review E 76.5 (2007): 056117](https://journals.aps.org/pre/abstract/10.1103/PhysRevE.76.056117).

hard
new algorithm
feature request

From [McCracken, James M., and Robert S. Weigel. "Nonparametric causal inference for bivariate time series." Physical Review E 93.2 (2016): 022207](https://journals.aps.org/pre/abstract/10.1103/PhysRevE.93.022207).

hard
new algorithm
feature request

We should implement [variation of information](https://en.wikipedia.org/wiki/Variation_of_information). It is a slight variation on mutual information, and straight-forward to implement once the new API is in place for V2.

association measures
feature request

In [this](https://ieeexplore.ieee.org/ielaam/18/9098132/8855009-aam.pdf) paper, Zhao and Lai propose to use a truncated version of the KL-estimator in cases where some samples are far away from other samples. The truncation involves setting...

new estimator
feature request

I just came across this paper: "Robust inference of causality in high-dimensional dynamical processes from the Information Imbalance of distance ranks" https://arxiv.org/abs/2305.10817. I haven't read it yet, but judging from...

feature request