BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Neyman-Pearson Classification  - Xin Tong\, University of Southern
  California
DTSTART:20200508T130000Z
DTEND:20200508T140000Z
UID:TALK140251@talks.cam.ac.uk
CONTACT:Dr Sergio Bacallado
DESCRIPTION:In many binary classification applications\, such as disease d
 iagnosis and spam detection\, practitioners commonly face the need to limi
 t type I error (that is\, the conditional probability of misclassifying a 
 class 0 observation as class 1) so that it remains below a desired thresho
 ld. To address this need\, the Neyman-Pearson (NP) classification paradigm
  is a natural choice\; it minimizes type II error (that is\, the condition
 al probability of misclassifying a class 1 observation as class 0) while e
 nforcing an upper bound\, alpha\, on the type I error. Although the NP par
 adigm has a century-long history in hypothesis testing\, it has not been w
 ell recognized and implemented in classification schemes. Common practices
  that directly limit the empirical type I error to no more than alpha do n
 ot satisfy the type I error control objective because the resulting classi
 fiers are still likely to have type I errors much larger than alpha.  This
  talk introduces the speaker and coauthors' work on NP classification algo
 rithms and their applications and raises current challenges under the NP p
 aradigm.  
LOCATION:https://zoom.us/j/95022384263?pwd=N3Z6elB2Vy9Jajd6azlCNjFHQVlKdz0
 9
END:VEVENT
END:VCALENDAR