Fast and robust Bayesian Inference using Gaussian Processes with GPry
Preprint
Abstract
We present the GPry algorithm for fast Bayesian inference of general (non-Gaussian) posteriors with a moderate number of parameters. GPry does not need any pre-training, special hardware such as GPUs, and is intended as a drop-in replacement for traditional Monte Carlo methods for Bayesian inference. Our algorithm is based on generating a Gaussian Process surrogate model of the log-posterior, aided by a Support Vector Machine classifier that excludes extreme or non-finite values. An active learning scheme allows us to reduce the number of required posterior evaluations by two orders of magnitude compared to traditional Monte Carlo inference. Our algorithm allows for parallel evaluations of the posterior at optimal locations, further reducing wall-clock times. We significantly improve performance using properties of the posterior in our active learning scheme and for the definition of the GP prior. In particular we account for the expected dynamical range of the posterior in different dimensionalities. We test our model against a number of synthetic and cosmological examples. GPry outperforms traditional Monte Carlo methods when the evaluation time of the likelihood (or the calculation of theoretical observables) is of the order of seconds; for evaluation times of over a minute it can perform inference in days that would take months using traditional methods. GPry is distributed as an open source Python package (pip install gpry) and can also be found at https://github.com/jonaselgammal/GPry.Keywords
All Related Versions
This publication has 57 references indexed in Scilit:
- Bayesian evidence-driven likelihood selection for sky-averaged 21-cm signal extractionPublications of the Astronomical Society of Australia, 2023
- Kernel-based emulator for the 3D matter power spectrum from CLASSAstronomy and Computing, 2022
- Bayesian optimization with safety constraints: safe and automatic parameter tuning in roboticsMachine Learning, 2021
- The imperative to reduce carbon emissions in astronomyNature Astronomy, 2020
- The ecological impact of high-performance computing in astrophysicsNature Astronomy, 2020
- The frontier of simulation-based inferenceProceedings of the National Academy of Sciences, 2020
- Dynamic nested sampling: an improved algorithm for parameter estimation and evidence calculationStatistics and Computing, 2018
- Planck2013 results. XV. CMB power spectra and likelihoodAstronomy & Astrophysics, 2014
- CosmoHammer: Cosmological parameter estimation with the MCMC HammerAstronomy and Computing, 2013
- Kriging Is Well-Suited to Parallelize Optimization2010