Skip to content

Introduction

gmm-divergence provides utilities for working with Gaussian mixture models and estimating divergences between them.

The package currently includes:

  • typed Gaussian and Gaussian mixture representations
  • density, log-density, and sampling utilities
  • KL divergence estimators for Gaussian mixtures
  • mixture-weight fitting against a target mixture

Active development

APIs, estimators, and numerical behavior may change between early releases.

Next steps

  • Getting started

    A quick introduction to the package, its features, and how to get started.

  • Kl estimation

    Estimate the KL divergence between two Gaussian mixtures using various numerical methods.

  • Mixture weight fitting

    Fit the mixture weights of a Gaussian mixture to minimize KL divergence against a target mixture.

  • API reference

    Jump into the generated Python API docs when you already know the area you want to inspect in code.