Please note: This seminar will take place in DC 1304.
Zaid Harchaoui, Professor
Department of Statistics, University of Washington
Classical supervised machine learning starts from a collection of input-output data pairs corresponding to a well-defined task. Predictive accuracy then scales as the number of datapoints, the size of the function class, and the number of optimization steps all increase in appropriate relative proportions. A new learning and prediction paradigm has gained tremendous momentum over the last decade, where one can learn a highly predictive model without task-specific data — or even a formal definition of the target task.
This new paradigm, called zero-shot prediction, has been successful both for known and unsuspected reasons. Starting from its origins in matching words and pictures, through recent self-supervised and contrastive learning approaches, I will describe key components driving its empirical performance in AI domains such as computer vision and language modeling and highlight current opportunities and challenges in this approach.
Bio: Zaid Harchaoui is a professor at the University of Washington in Seattle, in the Department of Statistics, the Paul G. Allen School of Computer Science and Engineering, the Department of Mathematics (dual appointments), and a Senior Data Science Fellow in the eScience Institute. He is an action editor at the Journal of Machine Learning Research. He is a principal investigator and a cofounder of IFML, the NSF-AI Institute on Foundations of Machine Learning.
He obtained the doctoral degree from Institut Polytechnique de Paris - Telecom Paris, for his research performed at CNRS - the French National Institute for Fundamental Research. He previously held appointments at the Courant Institute of Mathematical Sciences at New York University, at INRIA - the French National Institute for Research in Digital Science and Technology, and at Carnegie Mellon University. His research has received awards and recognitions from Neurips, ICML, IEEE, and ASA. He has received fellowships from CIFAR, Google, and the Simons Foundation.