BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Economics | IP Paris - ECPv5.1.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Department of Economics | IP Paris
X-ORIGINAL-URL:https://econ.ip-paris.fr
X-WR-CALDESC:Events for Department of Economics | IP Paris
BEGIN:VTIMEZONE
TZID:Europe/Helsinki
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20241027T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20240122T150000
DTEND;TZID=Europe/Helsinki:20240122T163000
DTSTAMP:20240521T130421
CREATED:20240119T115638Z
LAST-MODIFIED:20240119T115638Z
UID:15262-1705935600-1705941000@econ.ip-paris.fr
SUMMARY:Eugène NDIAYE (Apple Research) "Finite Sample Confidence Sets with "Minimal" Assumptions on the Distribution"
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 3:00 pm – 4:00 pm\nDate: 22th January 2024\nPlace: 3001 \n \nEugène NDIAYE (Apple Research) “Finite Sample Confidence Sets with “Minimal” Assumptions on the Distribution“ \n \n Abstract: \nIf you predict a label y of a new object with $hat{y}$\, how confident are you that ”y = $hat{y}$”? The conformal prediction method provides an elegant framework for answering such a question by establishing a confidence set for an unobserved response of a feature vector based on previous similar observations of responses and features. This is performed without assumptions about the distribution of the data. While providing strong coverage guarantees\, computing conformal prediction sets requires adjusting a predictive model to an augmented dataset considering all possible values that the unobserved response can take\, and proceeding to select the most likely ones. For a regression problem where y is a continuous variable\, it typically requires an infinite number of model fits; which is usually infeasible. By assuming a little more regularity in the underlying prediction models\, I will describe some of the techniques that make the calculations feasible. Along similar lines\, it can be assumed that we are working with a parametric model that explains the relation between input and output variables. Consequently\, a natural question arises as to whether a confidence interval on the ground truth parameter of the model can be constructed\, also without assumptions on the distribution of the data. In this presentation\, I will provide a partial answer to the question with some preliminary results. This is mostly an ongoing project\, with still a lot of open questions that I am eager to discuss and share insights for future work. \n \nOrganizers: \nKarim LOUNICI (CMAP) \, Jaouad MOURTADA (CREST) \nSponsors:\nCREST-CMAP \n
URL:https://econ.ip-paris.fr/event/eugene-ndiaye-apple-research-finite-sample-confidence-sets-with-minimal-assumptions-on-the-distribution-2/
CATEGORIES:Seminars,Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR