BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//IEEE Toronto Section - ECPv6.15.17//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.ieeetoronto.ca
X-WR-CALDESC:Events for IEEE Toronto Section
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20230101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20241218T100000
DTEND;TZID=UTC:20241218T120000
DTSTAMP:20260522T051400
CREATED:20241212T023128Z
LAST-MODIFIED:20241218T025143Z
UID:10000865-1734516000-1734523200@www.ieeetoronto.ca
SUMMARY:An Information Theoretic approach to Conformal Prediction
DESCRIPTION:Speaker: Arash Behboodi\, Director of Engineering at Qualcomm AI Research  Date and Time: Wednesday\, December 18\, 2024\, 10-11am  Location: BA-4164  Abstract: Conformal Prediction (CP) is a distribution-free uncertainty estimation framework that constructs prediction sets guaranteed to contain the true answer with a user-specified probability. Intuitively\, the size of the prediction set encodes a general notion of uncertainty\, with larger sets associated with higher degrees of uncertainty. In this work\, we leverage information theory to connect conformal prediction to other notions of uncertainty. More precisely\, we prove three different ways to upper bound the intrinsic uncertainty\, as described by the conditional entropy of the target variable given the inputs\, by combining CP with information theoretical inequalities. Moreover\, we demonstrate two direct and useful applications of such connection between conformal prediction and information theory: (i) more principled and effective conformal training objectives that generalize previous approaches and enable end-to-end training of machine learning models from scratch\, and (ii) a natural mechanism to incorporate side information into conformal prediction. We empirically validate both applications in centralized and federated learning settings\, showing our theoretical results translate to lower inefficiency (average prediction set size) for popular CP methods.  Bio: Arash Behboodi is a machine learning research scientist and Director of Engineering at Qualcomm AI Research. He received the Ph.D. degree in information theory from Ecole Superieure d’Electricite (now CentraleSuplec)\, France\, in 2012\, and a master’s degree in philosophy from Pantheon-Sorbonne university\, 2011. Prior to Qualcomm\, Arash was a senior researcher at Institute for Theoretical Information Technology in RWTH Aachen University and TU Berlin. He has been doing research on information\, machine learning and signal processing theory\, and recently focusing in particular on wireless AI\, inverse problems\, differentiable simulations\, and geometric deep learning. He has been a recipient of multiple best paper awards\, and organized multiple workshops on machine learning and other related topics.  Co-sponsored by: Prof. Ashish Khisti   Speaker(s): Arash Behboodi  Room: BA-4164\, Bldg: BA-4164\, University of Toronto\, Toronto\, Ontario\, Canada
URL:https://www.ieeetoronto.ca/event/an-information-theoretic-approach-to-conformal-prediction/
LOCATION:Room: BA-4164\, Bldg: BA-4164\, University of Toronto\, Toronto\, Ontario\, Canada
END:VEVENT
END:VCALENDAR