BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CREST - ECPv5.1.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:CREST
X-ORIGINAL-URL:https://crest.science
X-WR-CALDESC:Events for CREST
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20210328T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20211031T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20210111T140000
DTEND;TZID=Europe/Paris:20210111T151500
DTSTAMP:20210928T173016
CREATED:20210106T103451Z
LAST-MODIFIED:20210106T103451Z
UID:12501-1610373600-1610378100@crest.science
SUMMARY:Nicolas SCHREUDER (CREST) - "A minimax framework for quantifying risk-fairness trade-off in regression"
DESCRIPTION:\nThe Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:15 pm\nDate: 11th of January 2021\nPlace: Visio\nNicolas SCHREUDER (CREST) – “A minimax framework for quantifying risk-fairness trade-off in regression” \nAbstract: A theoretical framework is proposed for the problem of learning a real-valued function which meets fairness requirements. This framework is built upon the notion of $\alpha$-relative (fairness) improvement of the regression function which we introduce using the theory of optimal transport. Setting $\alpha = 0$ corresponds to the regression problem under the Demographic Parity constraint\, while $\alpha = 1$ corresponds to the classical regression problem without any constraints. For $\alpha \in (0\, 1)$ the proposed framework allows to continuously interpolate between these two extreme cases and to study partially fair predictors. Within this framework we precisely quantify the cost in risk induced by the introduction of the fairness constraint. We put forward a statistical minimax setup and derive a general problem-dependent lower bound on the risk of any estimator satisfying $\alpha$-relative improvement constraint. We illustrate our framework on a model of linear regression with Gaussian design and systematic group-dependent bias\, deriving matching (up to absolute constants) upper and lower bounds on the minimax risk under the introduced constraint. This talk is based on a joint work with Evgenii Chzhen\, see [arXiv:2007.14265]. \nOrganizers:\nCristina BUTUCEA (CREST)\, Alexandre TSYBAKOV (CREST)\, Karim LOUNICI (CMAP) \, Zoltan SZABO (CMAP)\nSponsors:\nCREST-CMAP\n \n\n
URL:https://crest.science/event/nicolas-schreuder/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR