- This event has passed.
ASSET Seminar: Domain Adaptation Under Causally Structured Distribution Shifts, Zachary Lipton (Carnegie Mellon University)
January 18, 2023 at 12:00 PM - 1:30 PM
Presentation Abstract:
Faced with unlabeled data in deployment that is sampled from a different distribution than that which generated the training data, all bets are off. Moreover, while numerous heuristics have been proposed for this vague setting, it remains unclear when any among them are applicable. One way to render these problems identifiable is to impose some (assumed) causal structure, both over how the variables are related to each other, which factors are potentially manipulable (and, complementarily, which are domain-invariant). Unlike conventional problems in causality, where the goal is to estimate the effect of a manipulation (a change in the policy for prescribing the treatment), here the manipulation has already happened, and our goal is to leverage the causal structure to adapt our predictors appropriately. In this talk, I will discuss some structures under which these problems are identifiable and some of the challenges (and solutions) for applying these ideas in deep learning settings.
Zachary Lipton
Assistant Professor, Machine Learning & Operations Research, Carnegie Mellon University
Zachary Chase Lipton is the BP Junior Chair Assistant Professor of Operations Research and Machine Learning at Carnegie Mellon University. His research spans core machine learning methods and their social impact and addresses diverse application areas, including clinical medicine and natural language processing. Current research focuses include robustness under distribution shift, breast cancer screening, the effective and equitable allocation of organs, and the intersection of causal thinking and the messy high-dimensional data that characterizes modern deep learning applications. He is the founder of the Approximately Correct blog (approximatelycorrect.com) and a co-author of Dive Into Deep Learning, an interactive open-source book drafted entirely through Jupyter notebooks. Together with Falaah Arif Khan, he co-authored the satirical “Superheroes of Deep Learning” comic book (https://github.com/acmi-lab/superheroes-deep-learning). Find on Twitter (@zacharylipton) or GitHub (@zackchase).