CS Talk - Tim G. J. Rudner, New York University

Event time: 
Wednesday, April 3, 2024 - 4:00pm
AKW 200 See map
51 Prospect Street
New Haven, CT 06511
Event description: 

CS Talk
Tim G. J. Rudner
New York University

Host: Smita Krishnaswamy

Title: Probabilistic Methods for Trustworthy Machine Learning


Machine learning models, while effective in controlled environments, can fail catastrophically when exposed to unexpected conditions upon deployment. This lack of robustness, well-documented even in state-of-the-art models, can lead to severe harm in high-stakes, safety-critical application domains such as healthcare. This shortcoming raises two central questions: When do machine learning models fail, and how can we develop machine learning models we can trust?

In this talk, I will approach this question from a probabilistic perspective, stepping through ways to address deficiencies in trustworthiness that arise in model construction, training, and deployment. First, I will demonstrate how a probabilistic approach to model construction can reveal—and help mitigate—failures in neural network training. Next, I will show how to improve the trustworthiness of neural networks with data-driven, domain-informed prior distributions over model parameters. Finally, I will discuss how a probabilistic perspective on prediction can enable interpretability of vision-language model representations. Throughout this talk, I will highlight carefully designed evaluation procedures for assessing the trustworthiness of machine learning models in safety-critical settings.


Tim G. J. Rudner is a Data Science Assistant Professor and Faculty Fellow at New York University’s Center for Data Science and an AI Fellow at Georgetown University’s Center for Security and Emerging Technology. He conducted PhD research on probabilistic machine learning in the Department of Computer Science at the University of Oxford, where he was advised by Yee Whye Teh and Yarin Gal. The goal of his research is to create trustworthy machine learning models by developing methods and theoretical insights that improve the reliability, safety, transparency, and fairness of machine learning systems deployed in safety-critical settings. Tim holds a master’s degree in statistics from the University of Oxford and an undergraduate degree in applied mathematics and economics from Yale University. He is also a Qualcomm Innovation Fellow and a Rhodes Scholar.