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:913@fds.yale.edu
DTSTART;TZID=America/New_York:20260401T113000
DTEND;TZID=America/New_York:20260401T130000
DTSTAMP:20260324T140557Z
URL:https://fds.yale.edu/events/fds-colloquium-bartolomeo-stellato-princet
 on/
SUMMARY:FDS Colloquium: Bartolomeo Stellato (Princeton)\, "Data-Driven Pers
 pectives on First-Order Methods for Convex Optimization"
DESCRIPTION:\nAbstract: First-order methods are widely used in large-scale 
 convex optimization\, yet providing sharp guarantees on their convergence 
 behavior remains a key challenge. In many practical settings\, the same op
 timization problem is solved repeatedly with varying parameters\, naturall
 y modeled as draws from an unknown distribution. In this talk\, I present 
 two complementary approaches that use the observed convergence on a limite
 d number of problem instances to improve both the analysis and the design 
 of first-order methods. The first combines the performance estimation prob
 lem (PEP) with Wasserstein distributionally robust optimization into a con
 vex semidefinite program that produces probabilistic convergence bounds\, 
 unifying worst-case and average-case analysis. The second uses PAC-Bayes t
 heory to learn algorithm parameters\, such as step-sizes and warm-starts\,
  with provable generalization guarantees rooted in the convergence propert
 ies of the underlying operators. Together\, these lines of work connect cl
 assical tools from convex analysis and operator theory with ideas from sta
 tistical learning\, offering both tighter performance certificates and a p
 rincipled approach to algorithm tuning.\n\n\n\nSpeaker Bio: Bartolomeo Ste
 llato is an Assistant Professor in the Department of Operations Research a
 nd Financial Engineering at Princeton University. Previously\, he was a Po
 stdoctoral Associate at the MIT Sloan School of Management and Operations 
 Research Center. He holds a DPhil (PhD) in Engineering Science from the Un
 iversity of Oxford\, a MSc in Robotics\, Systems and Control from ETH Zür
 ich\, and a BSc in Automation Engineering from Politecnico di Milano. He d
 eveloped OSQP\, a widely used solver in mathematical optimization. His awa
 rds include a Sloan Research Fellowship\, the 2024 Beale — Orchard-Hays 
 Prize\, an ONR Young Investigator Award\, an NSF CAREER Award\, the 2024 P
 rinceton SEAS Howard B. Wentz Jr. Faculty Award\, the 2022 Franco Strazzab
 osco Young Investigator Award from ISSNAF\, a Princeton SEAS Innovation Aw
 ard in Data Science\, the 2021 Best Paper Award in Mathematical Programmin
 g Computation\, and the 2018 First Place Prize Paper Award in IEEE Transac
 tions on Power Electronics. His research focuses on data-driven computatio
 nal tools for mathematical optimization\, machine learning\, and optimal c
 ontrol.\n\n\n\n\n
CATEGORIES:FDS Events,Colloquium
LOCATION:Yale Institute for Foundations of Data Science & Webcast\, 219 Pro
 spect Street\, 13th Floor\, New Haven\, CT\, 06511\, United States
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=219 Prospect Street\, 13th 
 Floor\, New Haven\, CT\, 06511\, United States;X-APPLE-RADIUS=100;X-TITLE=
 Yale Institute for Foundations of Data Science & Webcast: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