BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260603T005924EDT-2779CXi8TV@132.216.98.100
DTSTAMP:20260603T045924Z
DESCRIPTION:Title: Learning from a Biased Sample.\n\nAbstract:\n\nAbstract:
 \n\nThe empirical risk minimization approach to data-driven decision makin
 g assumes that we can learn a decision rule from training data drawn under
  the same conditions as the ones we want to deploy it under. However\, in 
 a number of settings\, we may be concerned that our training sample is bia
 sed\, and that some groups (characterized by either observable or unobserv
 able attributes) may be under- or over-represented relative to the general
  population\; and in this setting empirical risk minimization over the tra
 ining set may fail to yield rules that perform well at deployment. Buildin
 g on concepts from distributionally robust optimization and sensitivity an
 alysis\, we propose a method for learning a decision rule that minimizes t
 he worst-case risk incurred under a family of test distributions whose con
 ditional distributions of outcomes given covariates differ from the condit
 ional training distribution by at most a constant factor\, and whose covar
 iate distributions are absolutely continuous with respect to the covariate
  distribution of the training data. We apply a result of Rockafellar and U
 ryasev to show that this problem is equivalent to an augmented convex risk
  minimization problem. We give statistical guarantees for learning a robus
 t model using the method of sieves and propose a deep learning algorithm w
 hose loss function captures our robustness target. We empirically validate
  our proposed method in simulations and a case study with the MIMIC-III da
 taset.\n\n\n	https://mcgill.zoom.us/j/83436686293?pwd=b0RmWmlXRXE3OWR6NlNIc
 WF5d0dJQT09\n\n\n \n\n\n	Meeting ID: 834 3668 6293\n\n\n \n\n\n	Passcode: 12
 345\n\n\n \n\n\n	\n		\n			\n				 \n\n				 \n			\n		\n	\n\n
DTSTART:20230203T203000Z
DTEND:20230203T213000Z
SUMMARY:Lihua Lei (at Stanford Graduate School of Business)
URL:/mathstat/channels/event/lihua-lei-stanford-gradua
 te-school-business-345651
END:VEVENT
END:VCALENDAR