BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:How good is your classifier? Revisiting the role of evaluation met
 rics in machine learning - Sanmi Koyejo\, University of Illinois 
DTSTART:20190731T100000Z
DTEND:20190731T110000Z
UID:TALK128293@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:With the increasing integration of machine learning into real 
 systems\, it is crucial that trained models are optimized to reflect real-
 world tradeoffs. Increasing interest in proper evaluation has led to a wid
 e variety of metrics employed in practice\, often specially designed by ex
 perts. However\, modern training strategies have not kept up with the\nexp
 losion of metrics\, leaving practitioners to resort to heuristics.\nTo add
 ress this shortcoming\, I will present a simple\, yet consistent post-proc
 essing rule which improves the performance of trained binary\, multilabel\
 , and multioutput classifiers. Building on these results\, I will propose 
 a framework for metric elicitation\, which addresses the broader question 
 of how one might select an evaluation metric for real\nworld problems so t
 hat it reflects true preferences.\n
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR