Event Details:
Tuesday, November 1, 2022
8:30am - 9:30am PDT
This event is open to:
General Public
Free and open to the public
Tuesday, November 1, 2022 [Link to join] (ID: 996 2837 2037, Password: 386638)
- Speaker: Kun Zhang (CMU)
- Title: Methodological advances in causal representation learning
- Discussant: Victor Veitch (University of Chicago)
- Abstract: Causal representation learning aims to reveal the underlying high-level hidden causal variables and their relations. It can be seen as a special case of causal discovery, whose goal is to recover the underlying causal structure or causal model from observational data. The modularity property of a causal system implies properties of minimal changes and independent changes of causal representations, and how such properties make it possible to recover the underlying causal representations from observational data with identifiability guarantees: under appropriate assumptions, the learned representations are consistent with the underlying causal process. The talk will consider various problem settings involving independent and identically distributed (i.i.d.) data, temporal data, or data with distribution shift as input, and demonstrate when identifiable causal representation learning can benefit from the flexibility of deep learning and when it has to impose suitable parametric assumptions on the causal process.
Related Topics
Explore More Events
-
Lecture
Data Feminism for AI
-John A. and Cynthia Fry Gunn Rotunda, E241 at the ChEM-H / Neuro, 290 Jane Stanford Way, 2nd floor, Stanford, CA 94305 -
Conference
2024 Stanford Data Science Conference
-Paul Brest Hall (Law School), 555 Salvatierra Walk, Stanford, CA 94305 -
Causal Science Center
Bay Area Tech Economics Seminar
-John A. and Cynthia Fry Gunn Rotunda, E241 at the ChEM-H / Neuro, 290 Jane Stanford Way, 2nd floor, Stanford, CA 94305