BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//IFDS - ECPv6.0.1.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:IFDS
X-ORIGINAL-URL:https://ifds.info
X-WR-CALDESC:Events for IFDS
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20230312T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20231105T070000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20230306T123000
DTEND;TZID=America/Chicago:20230306T133000
DTSTAMP:20260410T053338
CREATED:20230313T144711Z
LAST-MODIFIED:20230313T145119Z
UID:2449-1678105800-1678109400@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:(WID 4130)
URL:https://ifds.info/event/ifds-ideas-forum-24/
LOCATION:WI
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20230308T123000
DTEND;TZID=America/Chicago:20230308T133000
DTSTAMP:20260410T053338
CREATED:20230313T144715Z
LAST-MODIFIED:20230313T145157Z
UID:2450-1678278600-1678282200@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:JOINT WITH SILO: Orchard View 12:30-1:30
URL:https://ifds.info/event/ifds-ideas-forum-25/
LOCATION:WI
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20230313T123000
DTEND;TZID=America/Chicago:20230313T133000
DTSTAMP:20260410T053338
CREATED:20230313T144715Z
LAST-MODIFIED:20230313T145240Z
UID:2451-1678710600-1678714200@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:SPRING BREAK – NO MEETING
URL:https://ifds.info/event/ifds-ideas-forum-26/
LOCATION:WI
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20230320T123000
DTEND;TZID=America/Chicago:20230320T133000
DTSTAMP:20260410T053338
CREATED:20230313T144715Z
LAST-MODIFIED:20230313T153516Z
UID:2452-1679315400-1679319000@ifds.info
SUMMARY:IFDS Ideas Forum: Misha Khodak
DESCRIPTION:New Directions in Algorithms with Predictions: Learning and Privacy \n\n\n\n\n\nAbstract: A burgeoning paradigm in algorithm design is learning-augmented algorithms\, or algorithms with predictions\, where methods can take advantage of a (possibly imperfect) prediction about their instance. While past work has focused on using predictions to improve competitive ratios and runtime\, this talk addresses a different\, salient question: how do we learn the predictions themselves? We introduce an approach for co-designing learning-augmented algorithms with their own custom learning algorithms\, with the crucial step being to optimize nice surrogate losses bounding the algorithms’ costs. This leads to improved sample complexity bounds for several learning-augmented graph algorithms and the first learning-theoretic guarantees for page migration with predictions\, among other contributions. We also instantiate these ideas on the new direction of learning-augmented private algorithms\, where the goal is to reduce utility loss due to privacy rather than runtime. Our approach drives numerous insights on how to robustly incorporate external information to release better statistics of sensitive datasets\, which we verify empirically on the task of multiple quantile release.Bio: Misha Khodak is a PhD student in computer science at Carnegie Mellon University advised by Nina Balcan and Ameet Talwalkar. He studies foundations and applications of machine learning\, especially meta-learning and algorithm design. Misha is a recipient of the Facebook PhD Fellowship and has interned at Google Research – New York\, Microsoft Research – New England\, the Lawrence Livermore National Lab\, and the Princeton Plasma Physics Lab.
URL:https://ifds.info/event/ifds-ideas-forum-27/
LOCATION:CS 1240
CATEGORIES:IFDS Ideas Forum
END:VEVENT
END:VCALENDAR