[Statlist] Joint Research Seminar on Statistics - FDS talk by Bryon Aragam, Chicago Booth - 21 March 2024 - 16:15-17:15, ETH Zurich, HG D 1.2

Maurer Letizia |et|z|@m@urer @end|ng |rom ethz@ch
Thu Mar 14 10:28:02 CET 2024


We are glad to announce the following joint Research Seminar on Statistics - FDS talk

Title: "Statistical aspects of nonparametric latent variable models and causal representation learning“
by Bryon Aragam, Chicago Booth

Date and time: Thursday, 21 March 2024, 16:15-17:15
Place: ETH Zurich, HG D 1.2

Host: Sara van de Geer

Abstract: "One of the key paradigm shifts in statistical machine learning over the past decade has been the transition from handcrafted features to automated, data-​driven representation learning. A crucial step in this pipeline is to identify latent representations from observational data along with their causal structure. In many applications, the causal variables are not directly observed, and must be learned from data, often using flexible, nonparametric models such as deep neural networks. These settings present new statistical and computational challenges that will be focus of this talk. We will re-​visit the statistical foundations of nonparametric latent variable models as a lens into the problem of causal representation learning. We discuss our recent work on developing methods for identifying and learning causal representations from data with rigourous guarantees, and discuss how even basic statistical properties are surprisingly subtle. Along the way, we will explore the connections between causal graphical models, deep generative models, and nonparametric mixture models, and how these connections lead to a useful new theory for causal representation learning.“

Seminar website: https://math.ethz.ch/sfs/eth-foundations-of-data-science/events/eth-fds-seminar.html.

The lecture will be followed by an aperitif for the audience.


Please feel free to share this information and we would be delighted if you find the time and opportunity to attend.





More information about the Statlist mailing list