Probabilistic Numerics is the notion that computation itself can be described as a form of learning, from electronically produced data. This removes the conceptual separation between empirical and computational information. One advantage of this view that will be discussed in detail in the talk is that probabilistic numerical computation allows seamless inference across dynamical systems. This can provide significant efficiency gains in ``physics-informed'' versions of machine learning. On a more abstract level, the talk's central argument is that one should not think of a "solver" for PDEs or ODEs as an encapsulated piece of immutable code, but an interactive, adaptive part of the machine learning tool-chain.

Bio: Philipp Hennig holds the Chair for the Methods of Machine Learning at the University of Tübingen, and an adjunct position at the Max Planck Institute for Intelligent Systems. He received his PhD from the University of Cambridge in 2011, under the supervision of Sir David MacKay. Since his PhD, Hennig has been interested in the connection between computation and inference. His book "Probabilistic Numerics — Computation as Machine Learning" with Michael Osborne and Hans Kersting, will be published by Cambridge UP later this year.