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/Helsinki
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20230326T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20231029T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20230405T094500
DTEND;TZID=Europe/Helsinki:20230405T110000
DTSTAMP:20260711T074130
CREATED:20230329T121112Z
LAST-MODIFIED:20230403T075729Z
UID:14809-1680687900-1680692400@crest.science
SUMMARY:Claire BOYER (Sorbonne Université) - "Is interpolation benign for random forest regression ?"
DESCRIPTION:Statistical Seminar: \nTime: 09:45 am – 11:00 am\nDate: 5th of April 2023\nPlace: Room 3001 + ZOOM \n  \nClaire BOYER (Sorbonne Université) – “Is interpolation benign for random forest regression ?” \n  \nhttps://zoom.us/j/94418482642?pwd=WGxBcnh2bE5MMEhENTVYQm9sR1NyZz09  \n  \nAbstract: \nStatistical wisdom suggests that very complex models\, interpolating training data\, will be poor at predicting unseen examples.Yet\, this aphorism has been recently challenged by the identification of benign overfitting regimes\, specially studied in the case of parametric models: generalization capabilities may be preserved despite model high complexity.While it is widely known that fully-grown decision trees interpolate and\, in turn\, have bad predictive performances\, the same behavior is yet to be analyzed for Random Forests (RF).In this paper\, we study the trade-off between interpolation and consistency for several types of RF algorithms. Theoretically\, we prove that interpolation regimes and consistency cannot be achieved simultaneously for several non-adaptive RF. Since adaptivity seems to be the cornerstone to bring together interpolation and consistency\, we study interpolating Median RF which are proved to be consistent in the interpolating regime. This is the first result conciliating interpolation and consistency for RF\, highlighting that the averaging effect introduced by feature randomization is a key mechanism\, sufficient to ensure the consistency in the interpolation regime and beyond. Numerical experiments show that Breiman’s RF are consistent while exactly interpolating\, when no bootstrap step is involved. We theoretically control the size of the interpolation area\, which converges fast enough to zero\, giving a necessary condition for exact interpolation and consistency to occur in conjunction. \n  \n  \nOrganizers:\nCristina BUTUCEA (CREST)\, Alexandre TSYBAKOV (CREST)\, Karim LOUNICI (CMAP) \, Jaouad MOURTADA (CREST)\nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/claire-boyer-sorbonne-universite-is-interpolation-benign-for-random-forest-regression/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR