[Statlist] Research Seminar on Statistics - FDS Seminar joint talk with Bryon Aragam, University of Chicago - 21 March 2024

[Maurer Letizia]

We are pleased to announce and invite you to the following joint talk in our Research Seminar on Statistics - FDS seminar series:

„Statistical aspects of nonparametric latent variable models and causal representation learning“
by Bryon Aragam, University of Chicago

Date and Time: Thursday, 21 March 2024, 16.15 - 17.15 (Zurich)
Place: ETH Zurich, HG D 1.2

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.

https://math.ethz.ch/sfs/news-and-events/research-seminar.html

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