Kernel Stein Discrepancy descent
Project description
Code for the article : "Kernel Stein Discrepancy Descent"
Compat
This package has been developed and tested with python3.7
. It is therefore not guaranteed to work with earlier versions of python.
Install the repository on your machine
This package can easily be installed using pip
, with the following command:
pip install -e .
This will install the package and all its dependencies, listed in requirements.txt
.
Reproducing the figures of the paper
To run the ICA experiment, run
python examples/ica.py
To display the effects of different initializations, run
python examples/plot_init.py
To display the effects of several different initializations with different mixtures of gaussians, run
python examples/plot_minima.py
To compare the running times of algorithms, run
python examples/plot_quantitative_expe_gaussian.py
where you can change the number of trials n_expe
and the number of particles n_samples
To obtain the trajectory of different algorithms on a simple Gaussian density, run
python examples/plot_simple_gaussian.py
To see the behavior of the algorithm on skewed mixture of Gaussian run
python examples/plot_skewed.py
To see the effect of the annealing policy, run
python examples/plot_temperature.py
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for ksddescent-0.1.dev0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7a9cdb6021a8ad0bb2b02a72232390271dc42716ee126b36914f28e9ec57d95a |
|
MD5 | bedf2b932a6755732af33947e44ddf18 |
|
BLAKE2b-256 | 1e4c141ef352cb8b3b9561e45c7c0e48c7f4f9dc6de1629c23cf99c3e699a1af |