I am interested in algorithms that estimate and express uncertainty about the result of imprecise computations. Such imprecision can arise because the computational task is not analytically tractable, because a limited computational budget only allows a partial solution, or because the description of the task is itself imprecise to begin with. Probability measures provide the formal language for the description of such uncertainty. My group and I develop computer algorithms that take in and return probability measures; we call these probabilistic numerical methods.
On 1 May 2018, I was appointed as a Full Professor to the newly created Chair for the Methods of Machine Learning at the Computer Science department of the University of Tübingen. My new website there will be created soon. For the time being, I am also keeping an adjunct position at the Max Planck Institute for Intelligent Systems. Over the coming months, the research group will migrate to the University.
If you need a bio-blurb for your event web-page or a talk introduction, here's a suggestion (sorry if this sounds like grandstanding, I've repeatedly been asked for such a text):
Philipp Hennig holds the Chair for the Methods of Machine Learning at the University of Tübingen, Germany, and an adjunct position at the Max Planck Institute for Intelligent Systems. He studied physics in Heidelberg and at Imperial College, London, and received a PhD from the University of Cambridge, UK, in 2011, under the supervision of the late Sir David JC MacKay. Since that time, he has been interested in the notion of computation as information gathering and, with collaborators, has helped re-establish the field of probabilistic numerics. Philipp primarily works in the machine learning community, where his group has made several algorithmic contributions. He has held an Emmy Noether fellowship, a Max Planck Research grant, and, in 2017, was awarded an ERC Starting Grant by the European Commission.
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems