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:898@fds.yale.edu
DTSTART;TZID=America/New_York:20251201T153000
DTEND;TZID=America/New_York:20251201T170000
DTSTAMP:20251030T201058Z
URL:https://fds.yale.edu/events/sds-seminar-yuting-wei-pennsylvania/
SUMMARY:S&amp\;DS Seminar: Yuting Wei (Pennsylvania)\, "Transformers Meet I
 n-Context Learning: A Universal Approximation Theory
DESCRIPTION:\nAbstract: Modern large language models are capable of in-cont
 ext learning\, the ability to perform new tasks at inference time using on
 ly a handful of input-output examples in the prompt\, without any fine-tun
 ing or parameter updates. We develop a universal approximation theory to b
 etter understand how transformers enable in-context learning. For any clas
 s of functions (each representing a distinct task)\, we demonstrate how to
  construct a transformer that\, without any further weight updates\, can p
 erform reliable prediction given only a few in-context examples. In contra
 st to much of the recent literature that frames transformers as algorithm 
 approximators — i.e.\, constructing transformers to emulate the iteratio
 ns of optimization algorithms as a means to approximate solutions of learn
 ing problems — our work adopts a fundamentally different approach rooted
  in universal function approximation. This alternative approach offers app
 roximation guarantees that are not constrained by the effectiveness of the
  optimization algorithms being approximated\, thereby extending far beyond
  convex problems and linear function classes. Our construction sheds light
  on how transformers can simultaneously learn general-purpose representati
 ons and adapt dynamically to in-context examples.\n\n\n\nBio: Dr. Yuting W
 ei is an Associate Professor in the Statistics and Data Science Department
  at the Wharton School\, University of Pennsylvania. Prior to that\, Dr. W
 ei spent two years at Carnegie Mellon University as an assistant professor
  and one year at Stanford University as a Stein’s Fellow. She received h
 er Ph.D. in statistics at the University of California\, Berkeley. She was
  the recipient of the 2025 Gottfried E. Noether Early Career Scholar Award
 \, Google Research Scholar Award\, NSF Career award\, and the Erich L. Leh
 mann Citation from the Berkeley statistics department. Her research intere
 sts include high-dimensional and non-parametric statistics\, reinforcement
  learning\, and diffusion models.\n
CATEGORIES:FDS Events
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:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR