Adaptive Gaussian Process Approximation for Bayesian Inference with Expensive Likelihood Functions

By Hongqiao Wang, Jinglai Li. 2017

66 citations recorded by the source corpus.

Abstract We consider Bayesian inference problems with computationally intensive likelihood functions. We propose a Gaussian process (GP)–based method to approximate the joint distribution of the unknown parameters and the data, built on recent work (Kandasamy, Schneider, & Póczos, 2015). In particular, we write the joint density approximately as a product of an approximate posterior density and an exponentiated GP surrogate. We then provide an adaptive algorithm to construct such an approximation, where an active learning method is used to choose the design points. With numerical examples, we illustrate that the proposed method has competitive performance against existing approaches for Bayesian computation.

Subfields: Artificial Intelligence, Control and Systems Engineering, Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Gwonsoo Che
2. Hongseok Yang
3. Matthew J. Parkinson
4. Peter W. O'Hearn
5. Viktor Vafeiadis

In Control and Systems Engineering

1. Gwonsoo Che
2. Hongseok Yang

In Probabilistic & Bayesian Methods

1. Gwonsoo Che
2. Hongseok Yang
3. Frank D. Wood

Citations in the corpus

• Meta-Learning an Inference Algorithm for Probabilistic Programs (2021, methodology): “Recently, methods for meta-learning these techniques themselves from a collection of inference tasks have been developed (Wang et al., 2018; Gong et al., 2019).”