Search

Workshop

On Inductive Biases for Gaussian Processes from Differential Algebra

  • Markus Lange-Hegermann (inIT / TH OWL)
E1 05 (Leibniz-Saal)

Abstract

We consider the interplay between Gaussian processes, a classical stochastic framework with recent fame in machine learning, with differential algebra. We construct Gaussian process priors that concentrate their probability mass on solutions of certain linear differential equations, which yields a strong inductive bias in the learning algorithm. Technically, Gröbner basis algorithms yield a parametrizations of the solution sets of such differential equations, with is used to push forward a suitable Gaussian process. If time permits, we discuss control, boundary values, and parameter identification as applications.

Links

Saskia Gutzschebauch

Max Planck Institute for Mathematics in the Sciences Contact via Mail

Rida Ait El Manssour

Max Planck Institute for Mathematics in the Sciences

Marc Härkönen

Georgia Institute of Technology

Bernd Sturmfels

Max Planck Institute for Mathematics in the Sciences