BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Penn Engineering Events - ECPv6.15.18//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Penn Engineering Events
X-ORIGINAL-URL:https://seasevents.nmsdev7.com
X-WR-CALDESC:Events for Penn Engineering Events
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20220313T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20221106T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220916T120000
DTEND;TZID=America/New_York:20220916T130000
DTSTAMP:20260405T161532
CREATED:20220920T142355Z
LAST-MODIFIED:20220920T142355Z
UID:7349-1663329600-1663333200@seasevents.nmsdev7.com
SUMMARY:Theory Seminar- Aaron Roth (University of Pennsylvania)
DESCRIPTION:Abstract: \nDawid gives two conceptualizations for models of individual probabilities: “Group to Individual” and “Individual to Group”. A classical concern about the “Group to Individual” view of probability is the reference class problem: Given that we can empirically measure only averages over many individuals\, which group or “reference class” do we choose to average over when estimating the probability for an individual? Machine Learning on the other hand operates in the “Individual to Group” conceptualization: models purport to assign probabilities to individuals\, which can be aggregated over to obtain group probabilities. Multicalibration gives us a way to obtain models that predict individual probabilities that are consistent with an arbitrary number of reference classes. But (with finite data) it does not solve the “model multiplicity” problem: there may be multiple models that are multicalibrated that assign many people very different individual probabilities. How are we to adjudicate between such models? We argue that if two parties agree on the data distribution\, then they cannot agree to disagree on (very many) individual probabilities\, even given access only to a small number of samples from the distribution. \nJoint work with Alexander Tolbert and Scott Weinstein
URL:https://seasevents.nmsdev7.com/event/theory-seminar-aaron-roth-university-of-pennsylvania/
LOCATION:Room 401B\, 3401 Walnut\, 3401 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="The Warren Center":MAILTO:Lhoot@seas.upenn.edu
END:VEVENT
END:VCALENDAR