ABSTRACT
In this talk, I will present Imprecise Probabilities (IPs), from their historic philosophical motivations to their applications to frequentist and Bayesian statistics. In turn, I will explore how the statistical approaches to IPs allowed to start the field of Imprecise Probabilistic Machine Learning, and why such a field is of paramount importance in modern ML. I will provide plenty of references, together with some new results on the comparison between Conformal Prediction and Imprecise Probabilistic Machine Learning, and how the latter can be used to derive regions that are narrower than the conformal ones, while retaining the same probabilistic guarantees.
BIO
Michele Caprio is a Postdoc at the PRECISE Center of the University of Pennsylvania, under the guidance of Prof. Insup Lee. He is an incoming Lecturer (Assistant Professor) in Machine Learning at the Department of Computer Science of the University of Manchester. He is also part of the Manchester Centre for AI Fundamentals, and an incoming Supervisor at the UKRI AI Center for Doctoral Training in Decision Making for Complex Systems. His main research interests are Uncertainty Quantification in AI and ML, Probabilistic ML, and Imprecise Probabilities. In 2023, he won the IJAR Young Researcher Award, a prize awarded every two years to a young scholar who demonstrates excellence in research at an early stage of the scientific career.
|
