Event Details:
Tuesday, March 8, 2022
8:30am - 9:30am PST
This event is open to:
General Public
Free and open to the public
Tuesday, March 8, 2022 [Link to join] (ID: 996 2837 2037, Password: 386638)
- Speaker: Yuansi Chen (Duke University)
- Title: Domain adaptation under structural causal models
- Abstract: Domain adaptation (DA) arises as an important problem in statistical machine learning when the source data used to train a model is different from the target data used to test the model. Recent advances in DA have mainly been application-driven and have largely relied on the idea of a common subspace for source and target data. To understand the empirical successes and failures of DA methods, we propose a theoretical framework via structural causal models that enables analysis and comparison of the prediction performance of DA methods. This framework also allows us to itemize the assumptions needed for the DA methods to have a low target error. Additionally, with insights from our theory, we propose a new DA method called CIRM that outperforms existing DA methods when both the covariates and label distributions are perturbed in the target data. We complement the theoretical analysis with extensive simulations to show the necessity of the devised assumptions. Reproducible synthetic and real data experiments are also provided to illustrate the strengths and weaknesses of DA methods when parts of the assumptions in our theory are violated.
- [Paper]
Related Topics
Explore More Events
-
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 -
Causal Science Center
"Causalitea": Causality Networking Social
-Citrus Courtyard, Behind Wallenberg Hall