BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Submodularity for Machine Learning - Ed Snelson and Rich Turner
DTSTART:20101202T140000Z
DTEND:20101202T153000Z
UID:TALK26209@talks.cam.ac.uk
CONTACT:Shakir Mohamed
DESCRIPTION:Recently\, a fundamental problem structure has emerged as very
  useful in a variety of machine learning applications: Submodularity is an
  intuitive diminishing returns property\, stating that adding an element t
 o a smaller set helps more than adding it to a larger set. Similarly to co
 nvexity\, submodularity allows one to efficiently find provably\n(near-) o
 ptimal solutions for large problems.\n\nWe will give an introduction to th
 is topic covering:\n\nIntroduction: Why should you care about submodularit
 y?\n\nBasic theory of Submodular set functions: Definitions\, Operations p
 reserving submodularity\, relationship to convexity\n\nOptimisation: Examp
 le problems involving minimisation and maximisation of submodular function
 s.\n\nThe RCC will be based on the tutorial found here:\nhttp://www.submod
 ularity.org/\n
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR