BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Data Distribution Dependent Priors for Stable Learning
DTSTART:20170614T140000
DTEND:20170614T144500
DTSTAMP:20260407T091117Z
UID:116c96f2d2f38e7628cc0b1d36d48c6e023b2f998c785aa0da646006
CATEGORIES:Conferences - Seminars
DESCRIPTION:John Shawe-Taylor\, University College London\nPAC-Bayes is a 
 state-of-the-art framework for analysing the generalisation of learning al
 gorithms that incorporates the Bayesian approach\, yet provides statistica
 l learning bounds. One feature of the approach is that though the prior mu
 st be fixed\, we do not need to have an explicit expression for it\, only 
 to be able to bound the distance between prior and posterior. Furthermore\
 , the choice of prior only impacts the quality of the bound and not the va
 lidity of the results. We will discuss the implications of these observati
 ons describing ways in which the prior may be chosen to improve the qualit
 y of the bounds obtained. The application of these ideas to the stability 
 analysis for SVMs delivers a significant tightening of the well-known stab
 ility bounds.
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR