CS 201: Towards Causal Representation Learning, FRANCISCO LOCATELLO, Amazon AWS

Speaker: Francesco Locatello
Affiliation: Amazon AWS

ABSTRACT:

Nowadays there is strong cross-pollination between the machine learning and graphical causality fields, with increasing mutual interest to benefit from the respective advances. In this talk, I will first review fundamental concepts of causal inference and present new approaches for causal discovery using machine learning. Second, I will relate open problems in machine learning to concepts that are well studied in causal inference, showing compelling examples on zero-shot generalization of RL policies and fairness, and broadly discussing how causality can contribute to modern machine learning research. Third, I will introduce causal representation learning as an open problem for both communities: the discovery of high-level causal variables from low-level observations. Finally, I will discuss my work on learning (more) causal representations and the architectural innovations that are required to represent causal variables with neural networks.

BIO:

Dr Francesco Locatello is a Senior Applied Scientist at Amazon AWS where he leads the Causal Representation Learning research team. He obtained his PhD at ETH Zurich supervised by Gunnar Ratsch (ETH Zurich) and Bernhard Scholkopf (Max Planck Institute for Intelligent Systems). He held doctoral fellowships at the Max Planck ETH Center for Learning Systems, ELLIS, and received the Google PhD Fellowship in Machine Learning 2019. His research has won several awards, including a best paper award at ICML 2019 and the ETH medal for outstanding doctoral dissertation.

Hosted by Professor Stefano Soatto

Date/Time:
Date(s) - May 05, 2022
4:15 pm - 5:45 pm

Location:
3400 Boelter Hall
420 Westwood Plaza Los Angeles California 90095