Prof. Michele Caprio
Lecturer (Assistant Professor) at The University of Manchester
Speaker: Prof. Michele Caprio Date: 05-11-2025 11am-12pm (BST) Location: Department of Computer Science, CS1.01, University of Warwick, Coventry, UK
Imprecise Probabilistic Machine Learning – Being Precise about Imprecision
Abstract
In this talk, I will (briefly) talk about the history of Imprecise Probabilities (IPs), from their inception in Philosophy, to their later adoption in Statistics and other sciences. After that, I’ll make the case for why IPs are useful and indeed needed in (Probabilistic) Machine Learning methodology and theory. I will conclude with a recent result in Imprecise Probabilistic Machine Learning methodology concerning the use of sets of distributions to improve Conformal Prediction Regions for classification problems with ambiguous ground truth. The effectiveness of the results is testified by an application to a dermatology dataset.
About Prof. Michele Caprio
Michele is a Lecturer (Assistant Professor) in Machine Learning and Artificial Intelligence at The University of Manchester. His general interest is probabilistic machine learning, and in particular the use of Imprecise Probabilistic techniques to investigate the theory and methodology of uncertainty quantification in Machine Learning and Artificial Intelligence. Recently, he won the IJAR Young Researcher and the IMS New Researcher Awards, he was elected Fellow of the Cambridge Philosophical Society, and nominated Action Editor of TMLR and ToPML.