BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Penn Engineering Events - ECPv6.16.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Penn Engineering Events
X-ORIGINAL-URL:https://seasevents.nmsdev7.com
X-WR-CALDESC:Events for Penn Engineering Events
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250424T120000
DTEND;TZID=America/New_York:20250424T131500
DTSTAMP:20260602T073319
CREATED:20250131T222656Z
LAST-MODIFIED:20250131T222656Z
UID:13143-1745496000-1745500500@seasevents.nmsdev7.com
SUMMARY:IDEAS/STAT Optimization Seminar: "Negative Stepsizes Make Gradient-Descent-Ascent Converge"
DESCRIPTION:Zoom link: https://upenn.zoom.us/j/98220304722 \nAbstract: Solving min-max problems is a central question in optimization\, games\, learning\, and controls. Arguably the most natural algorithm is Gradient-Descent-Ascent (GDA)\, however since the 1970s\, conventional wisdom has argued that it fails to converge even on simple problems. This failure spurred the extensive literature on modifying GDA with extragradients\, optimism\, momentum\, anchoring\, etc. In contrast\, we show that GDA converges in its original form by simply using a judicious choice of stepsizes. \nThe key innovation is the proposal of unconventional stepsize schedules that are time-varying\, asymmetric\, and (most surprisingly) periodically negative. We show that all three properties are necessary for convergence\, and that altogether this enables GDA to converge on the classical counterexamples (e.g.\, unconstrained convex-concave problems). The core intuition is that although negative stepsizes make backward progress\, they de-synchronize the min/max variables (overcoming the cycling issue of GDA) and lead to a slingshot phenomenon in which the forward progress in the other iterations is overwhelmingly larger. This results in fast overall convergence. Geometrically\, the slingshot dynamics leverage the non-reversibility of gradient flow: positive/negative steps cancel to first order\, yielding a second-order net movement in a new direction that leads to convergence and is otherwise impossible for GDA to move in. Joint work with Henry Shugart. \n 
URL:https://seasevents.nmsdev7.com/event/ideas-stat-optimization-seminar-jason-altschuler/
LOCATION:Amy Gutmann Hall\, Room 414\, 3333 Chestnut Street\, Philadelphia\, 19104\, United States
CATEGORIES:Seminar,Colloquium
END:VEVENT
END:VCALENDAR