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:20200308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20191103T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:69cee26eb715a
DTSTART;TZID=America/Toronto:20200910T160000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20200910T160000
URL:https://uwaterloo.ca/statistics-and-actuarial-science/events/department
 -seminar-emma-jingfei-zhang-miami-university
SUMMARY:Department seminar by Emma Jingfei Zhang\, Miami University
CLASS:PUBLIC
DESCRIPTION:NETWORK RESPONSE REGRESSION FOR MODELING POPULATION OF NETWORKS
  WITH\nCOVARIATES\n\n-------------------------\n\nMultiple-network data ar
 e fast emerging in recent years\, where a\nseparate network over a common 
 set of nodes is measured for each\nindividual subject\, along with rich su
 bject covariates information.\nExisting network analysis methods have prim
 arily focused on modeling a\nsingle network\, and are not directly applica
 ble to multiple networks\nwith subject covariates.\n\nIn this talk\, we pr
 esent a new network response regression model\,\nwhere the observed networ
 ks are treated as matrix-valued responses\,\nand the individual covariates
  as predictors. The new model\ncharacterizes the population-level connecti
 vity pattern through a\nlow-rank intercept matrix\, and the parsimonious e
 ffects of subject\ncovariates on the network through a sparse slope tensor
 . We formulate\nthe parameter estimation as a non-convex optimization prob
 lem\, and\ndevelop an efficient alternating gradient descent algorithm. We
 \nestablish the non-asymptotic error bound for the actual estimator from\n
 our optimization algorithm. Built upon this error bound\, we derive the\ns
 trong consistency for network community recovery\, as well as the edge\nse
 lection consistency. We demonstrate the efficacy of our method\nthrough in
 tensive simulations and two brain connectivity studies.\n\nJoin Zoom Meeti
 ng\n[https://zoom.us/j/8442836948?pwd=MVdCUFFCbVFuSzduQjhDQnNNZ3J1QT09]\n\
 nMeeting ID: 844 283 6948\nPasscode: 318995
DTSTAMP:20260402T214102Z
END:VEVENT
END:VCALENDAR