Uploaded July 2024 | Updated November 2026, 4 hours ago
Computer Science Seminar Series
February 19, 2021
“Towards Trustworthy AI: Provably Robust Extrapolation for Decision-Making”
Anqi “Angie” Liu, California Institute of Technology
To create trustworthy AI systems, we must safeguard machine learning methods from catastrophic failures; for example, we must account for uncertainty and guarantee performance for safety-critical systems, like in autonomous driving and health care, before deploying these methods 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, Anqi "Angie" Liu 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. Liu will showcase the practicality of this framework in applications on agile robotic control and computer vision. She 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 research associate in the Department of Computing and Mathematical Sciences at the California Institute of Technology. She obtained her PhD from the Department of Computer Science of the University of Illinois at Chicago. She is interested in machine learning for safety-critical tasks and the societal impact of AI. She aims to design principled learning methods and to collaborate with domain experts to build more reliable systems for the real world. She has been selected as a 2020 Electrical Engineering and Computer Science Rising Star at the University of California, Berkeley. Her publications appear in prestigious machine learning venues like the Conference and Workshop on Neural Information Processing Systems, the International Conference on Machine Learning, the International Conference on Learning Representations, the Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence, and the International Conference on Artificial Intelligence and Statistics.
Computer Science Seminar Series
February 19, 2021
“Towards Trustworthy AI: Provably Robust Extrapolation for Decision-Making”
Anqi “Angie” Liu, California Institute of Technology
To create trustworthy AI systems, we must safeguard machine learning methods from catastrophic failures; for example, we must account for uncertainty and guarantee performance for safety-critical systems, like in autonomous driving and health care, before deploying these methods 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, Anqi "Angie" Liu 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. Liu will showcase the practicality of this framework in applications on agile robotic control and computer vision. She 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 research associate in the Department of Computing and Mathematical Sciences at the California Institute of Technology. She obtained her PhD from the Department of Computer Science of the University of Illinois at Chicago. She is interested in machine learning for safety-critical tasks and the societal impact of AI. She aims to design principled learning methods and to collaborate with domain experts to build more reliable systems for the real world. She has been selected as a 2020 Electrical Engineering and Computer Science Rising Star at the University of California, Berkeley. Her publications appear in prestigious machine learning venues like the Conference and Workshop on Neural Information Processing Systems, the International Conference on Machine Learning, the International Conference on Learning Representations, the Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence, and the International Conference on Artificial Intelligence and Statistics.










