DeLTA Seminar by Stefan Bauer
Speaker
Stefan Bauer, KTH Stockholm
Title
Towards Learning Causal Representations & Interactive Benchmarks
Abstract
Many questions in everyday life as well as in research are causal in nature: How would the climate change if we lower train prices or will my headache go away if I take an aspirin? Inherently, such questions need to specify the causal variables relevant to the question. A central problem for AI and many application areas is thus the discovery of high-level causal variables from low-level observations like pixel values. While deep neural networks have achieved outstanding success in learning powerful representations for prediction, they fail to explain the effect of interventions. This is reflected in a limited ability to transfer and generalize even between related tasks. As a way forward to learn causal representations from data, this talk will describe our recent advances of combining interventions and causal structure with deep learning based approaches, as well as our efforts to create real-world benchmarks for the interactive learning paradigm. The proposed algorithms and frameworks are widely applicable, with use cases ranging from fairness in algorithmic decision making to experimental design in drug discovery.
Bio
Stefan Bauer is currently an assistant professor at KTH Stockholm and a CIFAR Azrieli Global Scholar. Using and developing tools of causality and deep learning, his research focuses on the longstanding goal of artificial intelligence to design machines that can extrapolate experience across environments and tasks. He obtained his PhD in Computer Science from ETH Zurich and was awarded with the ETH medal for an outstanding doctoral thesis. Before that, he graduated with a BSc and MSc in Mathematics from ETH Zurich and a BSc in Economics and Finance from the University of London (LSE). During his studies, he held scholarships from the Swiss and German National Merit Foundation. In 2019, he won the best paper award at the International Conference of Machine Learning (ICML) and in 2020, he was the lead organizer of the real-robot-challenge.com, a robotics challenge in the cloud.
_____________________________
You can subscribe to DeLTA Seminar mailing list by sending an empty email to delta-seminar-join@list.ku.dk.
Online calendar: https://calendar.google.com/calendar/embed?src=c_bm6u2c38ec3ti4lbfjd13c2aqg%40group.calendar.google.com&ctz=Europe%2FCopenhagen
DeLTA Lab page: https://sites.google.com/diku.edu/delta
DeLTA is a research group affiliated with the Department of Computer Science at the University of Copenhagen studying diverse aspects of Machine Learning Theory and its applications, including, but not limited to Reinforcement Learning, Online Learning and Bandits, PAC-Bayesian analysis