Title: Probabilistic Simulation Methods for Scientific Machine Learning
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, ODEs or DAEs as an encapsulated piece of immutable code, but an interactive, adaptive part of the machine learning tool-chain.
Philipp Hennig holds the Chair for the Methods of Machine Learning at the University of Tübingen. Since his PhD (with Sir David MacKay, Cambridge, 2011), Hennig has been interested in the connection between computation and inference. Hennig’s work has been supported by Emmy Noether, Max Planck and ERC grants. He co-directs the Program for Theory, Algorithms and Computation at ELLIS, the European Laboratory for Learning and Intelligent Systems. His book “Probabilistic Numerics — Computation as Machine Learning” with Michael Osborne and Hans Kersting was published by Cambridge University Press this year.