Stay Informed:
Baskin Engineering COVID-19 Information and Resources
Campus Roadmap to Recovery
Zoom Links: Zoom Help | Teaching with Zoom | Zoom Quick Guide

Towards Trustworthy AI: Provably Robust Extrapolation for Decision Making

Speaker Name: 
Anqi (Angie) Liu
Speaker Title: 
Postdoctoral Scholar
Speaker Organization: 
Start Time: 
Friday, March 19, 2021 - 11:00am
End Time: 
Friday, March 19, 2021 - 12:15pm
Via Zoom Link
Lise Getoor


To create trustworthy AI systems, we must safeguard machine learning methods from catastrophic failures. For example, we must account for the uncertainty and guarantee the performance for safety-critical systems, like in autonomous driving and health care, before deploying them in the real world. A key challenge in such real-world applications is that the test cases are not well represented by the pre-collected training data.  To properly leverage learning in such domains, we must go beyond the conventional learning paradigm of maximizing average prediction accuracy with generalization guarantees that rely on strong distributional relationships between training and test examples.


In this talk, I will describe a distributionally robust learning framework that offers accurate uncertainty quantification and rigorous guarantees under data distribution shift. This framework yields appropriately conservative yet still accurate predictions to guide real-world decision-making and is easily integrated with modern deep learning.  I will showcase the practicality of this framework in applications on agile robotic control and computer vision.  I will also introduce a survey of other real-world applications that would benefit from this framework for future work.



Anqi (Angie) Liu is a postdoctoral scholar research associate at the Department of Computing and Mathematical Sciences in the California Institute of Technology. She obtained her Ph.D. from the Department of Computer Science of the University of Illinois at Chicago in 2018. She is interested in machine learning for safety-critical tasks and the societal impact of AI. She aims to design principled learning methods and collaborate with domain experts to build more reliable systems for the real world. She has been selected for the EECS Rising Star in UC Berkeley 2020. Her publication appears in prestigious machine learning conferences like Neurips, ICML, ICLR, AAAI, and AISTAT.

As a gentle reminder, please respect the privacy of faculty recruitment by not sharing the candidate status of our guests with others outside of our organization.

Zoom Link:

Event Type: