BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.0.1//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:956@fds.yale.edu
DTSTART;TZID=America/New_York:20260916T120000
DTEND;TZID=America/New_York:20260916T130000
DTSTAMP:20260915T151700Z
URL:https://fds.yale.edu/events/fds-colloquium-john-duchi-stanford/
SUMMARY:FDS Colloquium: John Duchi (Stanford)\, "Finding Stationary Points 
 in Stochastic Convex Optimization: Why and How"
DESCRIPTION:\n\n\nAbstract: In this talk\, I will discuss finding stationar
 y points of possibly non-differentiable stochastic convex functions. Motiv
 ation for solving such problems arises in modern “distribution free” s
 tatistical learning problems. We will highlight some of the challenges of 
 solving such problems\, including that subgradients of stochastic convex f
 unctions do not converge uniformly\, and also demonstrate some new geometr
 ic tools to show that solving the problem is in fact possible.\n\n\n\nBase
 d on the paper "Finding a stationary point of a stochastic convex problem"
  (arXiv:2607.06883)\, a&nbsp\;joint work with Felipe Areces and&nbsp\;Malo
 &nbsp\;Sommers.\n\n\n\nSpeaker Bio: John Duchi is an associate professor o
 f Statistics and Electrical Engineering at Stanford University. His work s
 pans statistical learning\, optimization\, information theory\, and comput
 ation\, with a few driving goals. (1) To discover statistical learning pro
 cedures that optimally trade between real-world resources — computat
 ion\, communication\, privacy provided to study participants — while
  maintaining statistical efficiency. (2) To build efficient large-scale op
 timization methods that address the spectrum of optimization\, machine lea
 rning\, and data analysis problems we face\, allowing us to move beyond be
 spoke solutions to methods that robustly work. (3) To develop tools to ass
 ess and guarantee the validity of — and confidence we should have in
  — machine-learned systems.\n\n\n\nFaculty Host: Ilias Zadik\n\n\n\n
 \n
CATEGORIES:Fellows Events,FDS Events,Colloquium
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:20260308T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR