BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:888@fds.yale.edu
DTSTART;TZID=America/New_York:20251006T160000
DTEND;TZID=America/New_York:20251006T170000
DTSTAMP:20250929T192834Z
URL:https://fds.yale.edu/events/sds-seminar-martin-wainwright-mit-2/
SUMMARY:S&amp\;DS Seminar: Martin Wainwright (MIT)\, "Wild Refitting for Bl
 ack Box Prediction"
DESCRIPTION:\nAbstract: Obtaining inferential guarantees on the performance
  of a prediction method is essential in practice. Modern predictive method
 s present barriers: (a) they are opaque\, so that a statistician is limite
 d to querying its predicted values only (with no further insight into the 
 method’s properties)\; (b) a severely limited number of refits\, due to 
 computational expense\; and (c) data can be heterogeneous. We describe a n
 ovel procedure for estimating the excess risk of any black box regression 
 method that overcomes these challenges\, and avoids any use of hold-out. I
 nspired by the wild bootstrap\, it uses Rademacher residual symmetrization
  to construct a synthetic dataset for refitting. Unlike the bootstrap\, it
  requires only a single refit\, and we give non-asymptotic guarantees on t
 he risk estimate. We illustrate its behavior for non-rigid structure-from-
 motion\, and plug-and-play image denoising using deep net priors.\n\n\n\nP
 re-print: https://arxiv.org/abs/2506.21460\n\n\n\n\n
CATEGORIES:FDS Events,Statistics & Data Science Seminar
LOCATION:Yale Institute for Foundations of Data Science\, Kline Tower 13th 
 Floor\, Room 1327\, New Haven\, CT\, 06511\, United States
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Kline Tower 13th Floor\, Ro
 om 1327\, New Haven\, CT\, 06511\, United States;X-APPLE-RADIUS=100;X-TITL
 E=Yale Institute for Foundations of Data Science:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
DTSTART:20250309T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR