Skip to yearly menu bar Skip to main content


Poster

A Nonparametric Conjugate Prior Distribution for the Maximizing Argument of a Noisy Function

Pedro Ortega · Tim Genewein · Jordi Grau-Moya · David Balduzzi · Daniel A Braun

Harrah’s Special Events Center 2nd Floor

Abstract:

We propose a novel Bayesian approach to solve stochastic optimization problems that involve finding extrema of noisy, nonlinear functions. Previous work has focused on representing possible functions explicitly, which leads to a two-step procedure of first, doing inference over the function space and second, finding the extrema of these functions. Here we skip the representation step and directly model the distribution over extrema. To this end, we devise a non-parametric conjugate prior where the natural parameter corresponds to a given kernel function and the sufficient statistic is composed of the observed function values. The resulting posterior distribution directly captures the uncertainty over the maximum of the unknown function.

Live content is unavailable. Log in and register to view live content