Meta-Learning Conjugate Priors for Few-Shot Bayesian Optimization

TL;DR

This paper introduces a meta-learning approach to automatically estimate informative conjugate priors for Bayesian Optimization, improving performance in data-scarce scenarios by efficiently learning prior distributions.

Contribution

It proposes a novel meta-learning method to automate the estimation of conjugate priors, enhancing Bayesian Optimization with fewer data.

Findings

Generated priors require fewer data to estimate shape parameters.

Meta-learned priors improve Bayesian Optimization efficiency.

Automated prior estimation reduces manual tuning effort.

Abstract

Bayesian Optimization is methodology used in statistical modelling that utilizes a Gaussian process prior distribution to iteratively update a posterior distribution towards the true distribution of the data. Finding unbiased informative priors to sample from is challenging and can greatly influence the outcome on the posterior distribution if only few data are available. In this paper we propose a novel approach to utilize meta-learning to automate the estimation of informative conjugate prior distributions given a distribution class. From this process we generate priors that require only few data to estimate the shape parameters of the original distribution of the data.