BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260930T120916EDT-3678bIbjhX@132.216.98.100
DTSTAMP:20260930T160916Z
DESCRIPTION:Statistical Optimization and Nonasymptotic Robustness.\n\n\n	Abs
 tract: Statistical optimization has received quite some interests recently
 . It refers to the case where hidden and local convexity can be discovered
  in most cases for nonconvex problems\, making polynomial algorithms possi
 ble. It relies on careful analysis of the geometry near global optima. In 
 this talk\, I will explore this direction by focusing on sparse regression
  problems in high dimensions. A computational framework named iterative lo
 cal adaptive majorize-minimization (I-LAMM) is proposed to simultaneously 
 control algorithmic complexity and statistical error. I-LAMM effectively t
 urns the nonconvex penalized regression problem into a series of convex pr
 ograms by utilizing the locally strong convexity of the problem when restr
 icting the solution set in an l1 cone. Computationally\, we establish a ph
 ase transition phenomenon: it enjoys linear rate of convergence after a su
 b-linear burn-in. Statistically\, it provides solutions with optimal stati
 stical errors. Extensions to robust regression will be discussed.\n\n
DTSTART:20171020T193000Z
DTEND:20171020T203000Z
LOCATION:Room 1205\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Qiang Sun  (University of Toronto)
URL:https://www.mcgill.ca/mathstat/channels/event/qiang-sun-university-toro
 nto-278686
END:VEVENT
END:VCALENDAR