UPDATE: Due to unforeseen circumstances, the April 4th lecture will be canceled. 

In machine learning, we use data to automatically find dependencies in the world, with the goal of predicting future observations. ML methods build on statistical dependencies, but one can try to go beyond this, assaying underlying causal structures. Causal models may be more robust to changes that occur in real-world data sets, and they thus play a central role in addressing some of the hard open problems of AI. Schölkopf will discuss implications of causal models for machine learning, as well as connections in the opposite direction, including the program of causal representation learning.

Bernhard Schölkopf’s scientific interests are in machine learning and causal inference. He has applied his methods to a number of fields, ranging from biomedical problems to computational photography and astronomy. Schölkopf researched at AT&T Bell Labs, at GMD FIRST in Berlin, and at Microsoft Research in Cambridge, U.K., before becoming a Max Planck Institute director in 2001. He is a member of the German National Academy of Sciences (Leopoldina) and has (co-)received the Royal Society Milner Award, the Leibniz Prize, the Körber European Science Prize, and the BBVA Foundation Frontiers of Knowledge Award. He is a fellow of the ACM and the CIFAR program Learning in Machines & Brains; he is also an Amazon distinguished scholar and holds a professorship at ETH Zurich. Schölkopf co-founded the Machine Learning Summer Schools series, and helped build the Journal of Machine Learning Research, an early development in open access and today the field’s flagship journal.

This event will be held in person and virtually. Zoom link to Join [here].

Please read on for important information regarding logistics for those planning to register to attend the workshop in-person at Calvin Lab.

Proof of Vaccination
Given current public health directives from state, local, and university authorities, all participants in Simons Institute events must be prepared to demonstrate proof of full vaccination: a vaccination card or photo of the card along with a valid photo ID, or a green or blue Campus Access Badge via the UC Berkeley Mobile app (additional details regarding proof of vaccination can be found here).

Masks
Masks are strongly encouraged for all participants. The latest masking requirements on campus can be found here.

Refreshments
Light refreshments will be provided before the lecture. Please note due to current health conditions, we will set up just outside the building. There will be signs to direct you. Please note there is no food or drink allowed in the auditorium. Thank you for helping us to keep the auditorium clean.

Please note: the Simons Institute regularly captures photos and video of activity around the Institute for use in videos, publications, and promotional materials.