BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Claremont Center for the Mathematical Sciences - ECPv6.15.17.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://colleges.claremont.edu/ccms
X-WR-CALDESC:Events for Claremont Center for the Mathematical Sciences
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20210314T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20211107T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20220313T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20221106T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20230312T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20231105T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20220202T161500
DTEND;TZID=America/Los_Angeles:20220202T173000
DTSTAMP:20260429T035210
CREATED:20220128T183638Z
LAST-MODIFIED:20220131T193506Z
UID:2581-1643818500-1643823000@colleges.claremont.edu
SUMMARY:Exploiting metric structure for more accurate classification (Prof. Mike Izbicki)
DESCRIPTION:Title: Exploiting metric structure for more accurate classification \nSpeaker: Mike Izbicki\, Department of Mathematical Sciences\, Claremont McKenna College \nAbstract: Classification problems often have many semantically similar classes.  For example\, the famous ImageNet dataset contains classes for 80 different dog breeds\, 40 different bird species\, and 25 types of vehicles.  This semantic structure can be formalized using a metric space\, with semantic similarity of classes encoded by the distance function.  In this talk\, I’ll describe the “tree loss”\, which is the first technique with provable performance guarantees for exploiting this metric structure.  I’ll also show that the tree loss has better empirical performance than competing algorithms on image\, text\, and vector data. \n\nMike studies machine learning theory\, focusing on applications to natural language and social media.  He has been at CMC for 3 years now\, where he teaches computer and data science classes.  Prior to his academic career\, Mike spent 7 years in the US Navy.  Highlights include converting >10g of Uranium into pure energy as a nuclear submarine officer\, and doing [redacted] for the NSA.  After leaving the navy\, Mike went to North Korea to teach computer science as part of an academic exchange program designed to improve relations between the US and North Korea.  He earned his phd from UC Riverside.
URL:https://colleges.claremont.edu/ccms/event/exploiting-metric-structure-for-more-accurate-classification-prof-mike-izbicki/
LOCATION:Zoom meeting\, United States
CATEGORIES:Colloquium
END:VEVENT
END:VCALENDAR