jaxns
A JAX-based probabilistic programming framework using nested sampling for fast Bayesian inference and evidence computation.
What is jaxns?
JAXNS is a probabilistic programming framework implemented in JAX that uses nested sampling for Bayesian inference. It allows users to define probabilistic models and compute Bayesian evidence, posterior samples, and perform model selection with high performance due to JAX's JIT compilation to XLA. The framework solves the problem of slow traditional nested sampling methods by leveraging hardware acceleration and advanced algorithms like Phantom-Powered Nested Sampling.
Researchers, data scientists, and developers working in Bayesian statistics, probabilistic machine learning, or scientific computing who need efficient nested sampling for model comparison and parameter inference.
Developers choose JAXNS for its speed (orders of magnitude faster than PolyChord, MultiNEST, and dynesty), flexibility in model definition, and ability to handle complex, multi-modal posteriors with gradient-based optimisation and evidence maximisation.
Overview
Probabilistic Programming and Nested sampling in JAX
Use Cases
Best For
- Computing Bayesian evidence for model comparison and hypothesis testing
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
