BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Statistical Learning Theory - Maria Lomeli
DTSTART:20180215T133000Z
DTEND:20180215T150000Z
UID:TALK94240@talks.cam.ac.uk
CONTACT:Alessandro Davide Ialongo
DESCRIPTION:*Abstract*\n\nThe wikipedia definition of Statistical Learning
  Theory says that it is a framework for machine learning drawing from the 
 fields of statistics and functional analysis. It deals with the problem of
  finding a predictive function based on data. According to Vapnik (1990)\,
  "abstract learning theory established some conditions for generalization 
 which are more general than those discussed in classical statistical parad
 igms and the understanding of these conditions inspired new algorithmic ap
 proaches to function estimation problems."\nI will cover some introductory
  material\, including the following topics: \n\n\nDifferent loss functions
 \nLearning algorithms: Empirical risk minimisation and regularisation \nHo
 w can we solve each problem (first order methods only)\nVC dimension and s
 ome bounds\n\n*Recommended Reading*\n\n"Introduction to Statistical Learni
 ng Theory":http://www.kyb.mpg.de/fileadmin/user_upload/files/publications/
 pdfs/pdf2819.pdf\, Bousquet\, O.\, Boucheron\, S. and Lugosi\, G.\n\n"MIT 
 Statistical Learning Theory and Applications course":http://www.mit.edu/~9
 .520/fall17/ and "RegML summer school notes":http://lcsl.mit.edu/courses/r
 egml/regml2017/ by Lorenzo Rosasco\n\n"An Overview of Statistical Learning
  theory":http://www.mit.edu/~6.454/www_spring_2001/emin/slt.pdf\, Vapnik\,
  V.\n
LOCATION:Engineering Department\, CBL Seminar Room 4-38
END:VEVENT
END:VCALENDAR