Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Your Model is Wrong: Robustness and misspecification in probabilistic modeling

Invariant Priors for Bayesian Quadrature

Masha Naslidnyk · Javier González · Maren Mahsereci


Abstract:

Bayesian quadrature (BQ) is a model-based numerical integration method that is able to increase sample efficiency by encoding and leveraging known structure of the integration task at hand. In this paper, we explore priors that encode invariance of the integrand under a set of bijective transformations in the input domain, in particular some unitary transformations, such as rotations, axis-flips, or point symmetries. We show initial results on superior performance in comparison to standard Bayesian quadrature on several synthetic and one real world application.

Chat is not available.