BEGIN:VCALENDAR
PRODID:-//Columba Systems Ltd//NONSGML CPNG/SpringViewer/ICal Output/3.3-
 M3//EN
VERSION:2.0
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20240528T154408Z
DTSTART:20240605T093000Z
DTEND:20240605T103000Z
SUMMARY:AI-Fun Seminar | Michele Caprio: Imprecise Probabilistic Machine 
 Learning: Being Precise About Imprecision
UID:{http://www.columbasystems.com/customers/uom/gpp/eventid/}nb6-lwqkghu
 u-pzyfnm
DESCRIPTION:The Manchester Centre for AI Fundamentals is hosting a series
  of seminars featuring expert researchers working in the fundamentals of
  AI. \n\nTitle: Imprecise Probabilistic Machine Learning: Being Precise 
 About Imprecision.\nSpeaker: Michele Caprio\, The University of Manchest
 er (joining summer 2024).\n\nAbstract: This talk is divided into two par
 ts. I will first introduce the field of “Imprecise Probabilistic Machine
  Learning”\, from its inception to modern-day research and open problems
 \, including motivations and clarifying examples.\nIn the second part\, 
 I will present some recent results that I've derived together with colle
 agues at Oxford Brookes on Credal Learning Theory. Statistical Learning 
 Theory is the foundation of machine learning\, providing theoretical bou
 nds for the risk of models learned from a (single) training set\, assume
 d to issue from an unknown probability distribution. In actual deploymen
 t\, however\, the data distribution may (and often does) vary\, causing 
 domain adaptation/generalization issues. We laid the foundations for a c
 redal theory of learning\, using convex sets of probabilities (credal se
 ts) to model the variability in the data-generating distribution. Such c
 redal sets\, we argued\, may be inferred from a finite sample of trainin
 g sets. We derived bounds for the case of finite hypotheses spaces (both
  assuming realizability or not)\, as well as infinite model spaces\, whi
 ch directly generalize classical results. This talk is based on the foll
 owing work\, https://doi.org/10.48550/arXiv.2402.00957\n\nMichele is joi
 ning The University of Manchester and the Centre for AI Fundamentals in 
 summer 2024.
STATUS:TENTATIVE
TRANSP:TRANSPARENT
CLASS:PUBLIC
LOCATION:Emmeline Suite\, Christabel Pankhurst Building\, Dover Street \,
  Manchester
END:VEVENT
END:VCALENDAR