Output details

A comparative evaluation of stochastic-based inference methods for Gaussian process models

<24>Gaussian Processes are extensively employed for analysing data in several domains, such as life sciences and engineering. Quantification of uncertainty in model parameters and in predictions is of paramount importance to test scientific hypotheses. This is the first paper attempting to rigorously assess the efficiency of Markov chain Monte Carlo algorithms to infer parameters in Gaussian Process models.

This paper was accepted for publication in a very selective special issue of Machine Learning, which is one of the top journals in the field of machine learning; only 14 papers were accepted out of 182 submissions.