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:69f3aabdebf09
DTSTART;TZID=America/Toronto:20200312T160000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20200312T160000
URL:https://uwaterloo.ca/statistics-and-actuarial-science/events/department
 -seminar-matthew-pratola-ohio-state-university
LOCATION:M3 - Mathematics 3 200 University Avenue West Waterloo ON N2L 3G1 
 Canada
SUMMARY:Department seminar by Matthew Pratola\, Ohio State University 
CLASS:PUBLIC
DESCRIPTION: BAYESIAN ADDITIVE REGRESSION TREES FOR STATISTICAL LEARNING\n
 \nRegression trees are flexible non-parametric models that are well\nsuite
 d to many modern statistical learning problems. Many such tree\nmodels hav
 e been proposed\, from the simple single-tree model (e.g.\nClassification 
 and Regression Trees — CART) to more complex tree\nensembles (e.g. Rando
 m Forests). Their nonparametric formulation\nallows one to model datasets 
 exhibiting complex non-linear\nrelationships between predictors and the re
 sponse.  A recent\ninnovation in the statistical literature is the develo
 pment of a\nBayesian analogue to these classical regression tree models. 
  The\nbenefit of the Bayesian approach is the ability to quantify\nuncert
 ainties within a holistic Bayesian framework.  We introduce the\nmost pop
 ular variant\, the Bayesian Additive Regression Trees (BART)\nmodel\, and 
 describe recent innovations to this framework.  We\nconclude with some of
  the exciting research directions currently being\nexplored.
DTSTAMP:20260430T191717Z
END:VEVENT
END:VCALENDAR