Estimating constrained precision matrices using TensorFlow

This is the source repo. for the tfConstrainedGauss Python package.

It is a TensorFlow package for finding the interactions in a Gaussian graphical model with given and fixed structure from constraints on the precision matrix.

A detailed write up can be found in the PDF in the latex folder.

Quickstart

1. Install:

pip install tfConstrainedGauss

2. See the example notebooks in the example folder of the GitHub repo.

3. Scan the api_ref.

Requirements

• TensorFlow 2.5.0 or later. Note: later versions not tested.

• Python 3.7.4 or later.

Installation

Either: use pip:

pip install tfConstrainedGauss

Or alternatively, clone this repo. from GitHub and use the provided setup.py:

pip install .

API Documentation

See the api_ref.

Examples

See the notebooks in the examples directory in GitHub repo.

Indices and tables

• Index

• Module Index

• Search Page

Contents

Contents:

• tfConstrainedGauss
  • tfConstrainedGauss package