BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal iCal API//EN
X-WR-CALNAME:Events items teaser
X-WR-TIMEZONE:America/Toronto
BEGIN:VTIMEZONE
TZID:America/Toronto
X-LIC-LOCATION:America/Toronto
BEGIN:DAYLIGHT
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20241103T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:69cf6a64a86cf
DTSTART;TZID=America/Toronto:20250515T130000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20250515T143000
URL:https://uwaterloo.ca/combinatorics-and-optimization/events/co-reading-g
 roup-felix-zhou
SUMMARY:C&O Reading Group -Felix Zhou
CLASS:PUBLIC
DESCRIPTION:TITLE: Learning from Coarse Samples\n\nSPEAKER:\n Felix Zhou\n
 \nAFFILIATION:\n University of Waterloo\n\nLOCATION:\n MC 6029\n\nABSTRACT
 :Coarsening occurs when the exact value of a sample is not\nobserved.\nIns
 tead\, only a subset of the sample space containing the exact value\nis kn
 own.\nCoarse data naturally arises in diverse fields\, including Economics
 \,\nEngineering\, Medical and Biological Sciences\, and all areas of the\n
 Physical Sciences.\nOne of the simplest forms of coarsening is rounding\, 
 where data values\nare mapped to the nearest point on a specified lattice.
 \n\nWe survey applications of coarse learning to regression with\nself-sel
 ection bias\, regression with second-price auction data\, and\npresent det
 ails of an SGD-based algorithm for coarse Gaussian mean\nestimation.\n\nBa
 sed on joint work with Alkis Kalavasis and Anay Mehrotra\n(https://arxiv.o
 rg/abs/2504.07133)
DTSTAMP:20260403T072108Z
END:VEVENT
END:VCALENDAR