Prof. Chelsea Finn - Flexible Machine Learning for Mitigating Distribution Shift - Princeton AI Club

This talk has been given by Prof. Chelsea Finn on Zoom at Princeton AI Club on Friday 3rd June 2022, 1:00 PM EST

Follow us for more events on Twitter at:   / princetonaiclub  
Website with next events at: https://aiclub.princeton.edu/


Abstract of the talk:
While we have seen immense progress in machine learning, a critical shortcoming of current methods lies in handling distribution shift between training and deployment. Distribution shift is pervasive in real-world problems ranging from natural variation in the distribution over locations or domains, to shift in the distribution arising from different decision making policies, to shifts over time as the world changes. In this talk, I’ll discuss two classes of algorithms that can mitigate certain forms of distribution shift. The first leverages unlabeled test-distribution data to learn a diverse set of functions. In doing so, it is able to address major limitations of prior robustness works: it doesn’t require labeled data from the test distribution to tune hyperparameters, and it can handle an extreme version of spurious correlations where there is a perfect correlation between the spurious attribute and label. The second class of algorithms targets concept drift, i.e. when p(label | input) changes, by allowing practitioners to quickly “edit” a model. I will discuss methods for editing the behavior of neural networks, including two techniques that can edit large language models without re-training or fine-tuning.


Prof. Chelsea Finn's website: https://ai.stanford.edu/~cbfinn/

Bio:
Chelsea Finn is an Assistant Professor in Computer Science and Electrical Engineering at Stanford University, and the William George and Ida Mary Hoover Faculty Fellow. Finn’s research interests lie in the capability of robots and other agents to develop broadly intelligent behavior through learning and interaction. To this end, her work has included deep learning algorithms for concurrently learning visual perception and control in robotic manipulation skills, inverse reinforcement methods for learning reward functions underlying behavior, and meta-learning algorithms that can enable fast, few-shot adaptation in both visual perception and deep reinforcement learning. Finn received her Bachelor’s degree in Electrical Engineering and Computer Science at MIT and her PhD in Computer Science at UC Berkeley. Her research has been recognized through the Microsoft Research Faculty Fellowship, the IEEE RAS Early Academic Career Award, the ONR Young Investigator Award, the ACM doctoral dissertation award, and the MIT Technology Review 35 under 35 Award, and her work has been covered by various media outlets, including the New York Times, Wired, and Bloomberg. Throughout her career, she has sought to increase the representation of underrepresented minorities within CS and AI by developing an AI outreach camp at Berkeley for underprivileged high school students, a mentoring program for underrepresented undergraduates across four universities, and leading efforts within the WiML and Berkeley WiCSE communities of women researchers.