Search

Bernhard Schölkopf

Scholkopf_BW

Appointment

  • Fellow
  • Learning in Machines & Brains

Institution

  • ETH Zurich
  • Max Planck Institute for Intelligent Systems
Department of Empirical Inference

Country

  • Germany

Education

M. Sc. Mathematics, Diplom Physics;
Ph.D. Computer Science

About

Bernhard Schölkopf's scientific interests are in machine learning and causal inference.

He has applied his methods to a number of different fields, ranging from biomedical problems to computational photography and astronomy. Bernhard has researched at AT&T Bell Labs, at GMD FIRST, Berlin, and at Microsoft Research Cambridge, UK, before becoming a Max Planck director in 2001. He is a member of the German Academy of Sciences (Leopoldina) and a Fellow of the ACM.

Bernhard co-founded the series of Machine Learning Summer Schools, and currently acts as co-editor-in-chief for the Journal of Machine Learning Research, an early development in open access and today the field's flagship journal.

Photo: David Ausserhofer

Awards

Annual PhD Award of the German Computer Science Association, 1998

J. K. Aggarwal Prize of the International Association for Pattern Recognition, 2006

Academy Prize of the Berlin-Brandenburg Academy of Sciences and Humanities, 2012

Royal Society Milner Award 2014

Leibniz Prize 2018

Relevant Publications

J. Peters, D. Janzing, and B. Schölkopf. Elements of Causal Inference - Foundations and Learning Algorithms. MIT Press, Cambridge, MA, USA, 2017

B. Schölkopf, D. Hogg, D. Wang, D. Foreman-Mackey, D. Janzing, C.-J. Simon-Gabriel, and J. Peters. Modeling confounding by half-sibling regression. Proceedings of the National Academy of Science (PNAS), 13(27):7391–7398, 2016

B. Schölkopf, D. Janzing, J. Peters, E. Sgouritsa, K. Zhang, and J. Mooij. On causal and anticausal learning. In J. Langford and J. Pineau, editors, Proceedings of the 29th International Conference on Machine Learning (ICML), pages 1255–1262, New York, NY, USA, 2012. Omnipress

D. Janzing and B. Schölkopf. Causal inference using the algorithmic Markov condition. IEEE Transactions on Information Theory, 56(10):5168–5194, 2010

B. Schölkopf and A. J. Smola. Learning with Kernels. MIT Press, Cambridge, MA, USA, 2002

Connect

Website