ECE SEMINAR

Abstract
The talk will be self-contained and no background on conformal prediction is required. Conformal prediction is a mathematical framework for uncertainty quantification of machine learning models. Originated from Statistics, this framework is now considered as one of the main tools for constructing uncertainty sets around the predictions obtained by modern machine learning models such as deep neural networks and large language models.

My goal in this talk is to (i) provide a detailed introduction to conformal prediction and cover a few of the central ideas in this area, and (ii) explain one of our recent algorithmic results in this area on constructing (near-) optimal uncertainty sets in terms of size.

Methods in conformal prediction are often founded on probabilistic relations and laws. Consequently, this area could be an interesting avenue for theorists to explore and contribute to.

Bio
Hamed Hassani is currently an associate professor ofthe Electrical and Systems Engineering Department, the Computer and Information Systems Department, and the Department of Statistics and Data Science at the Universityof Pennsylvania. Prior to that, he was a research fellow at Simons Institute for the Theory of Computing (UC Berkeley) affiliated with the program of Foundations of Machine Learning, and a post-doctoral researcher at the Institute ofMachine Learning at ETH Zurich. He received a Ph.D. degree in Computer and Communication Sciences from EPFL, Lausanne. He is the recipient of the 2014 IEEE Information Theory Society Thomas M. Cover Dissertation Award, 2015 IEEE International Symposium on Information Theory Student Paper Award, 2017 Simons- Berkeley Fellowship, 2018 NSF-CRII Research Initiative Award, 2020 Air Force Office of Scientific Research (AFOSR) Young Investigator Award, 2020 National Science Foundation (NSF) CAREER Award, 2020 Intel Rising Star award, the distinguished lecturer of the IEEE Information Society in 2022-23, and the 2023 IEEE Communications Society & Information theory Society Joint Paper Award. Moreover, he was selected as the recipient of the 2023 IEEE Information Theory Society's James L. Massey Research and Teaching Award for Young Scholars.