LogDensityProblems.jl

A common framework for implementing and using log densities for inference.
Author tpapp
Popularity
17 Stars
Updated Last
1 Year Ago
Started In
July 2018

LogDensityProblems.jl

Lifecycle lifecycle build codecov.io Documentation Documentation

A common framework for implementing and using log densities for inference, providing the following functionality.

  1. The logdensity method with corresponding interface, which can be used by other packages that operate on (log) densities and need to evaluate the log densities or the gradients (eg MCMC, MAP, ML or similar methods).

  2. The ADgradient which makes objects that support logdensity to calculate log density values calculate log density gradients using various automatic differentiation packages.

  3. The wrapper TransformedLogDensity using the TransformVariables.jl package, allowing callables that take a set of parameters transformed from a flat vector of real numbers to support the logdensity interface.

  4. Various utility functions for debugging and testing log densities.

See the documentation for details.