BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20241027T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250330T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.28685.field_data.0@www.diag.uniroma1.it
DTSTAMP:20260407T212926Z
CREATED:20250312T121454Z
DESCRIPTION:NELL’AMBITO DELLA PROCEDURA SELETTIVA DI CHIAMATA\, AI SENSI DE
 L NOVELLATO ART. 24\, COMMA 3\, LEGGE 240/2010\, PER N. 1 POSTO DI RICERCA
 TORE A TEMPO DETERMINATO IN TENURE TRACK (RTT) PER IL GRUPPO SCIENTIFICO D
 ISCIPLINARE 09/IINF-05 - SETTORE SCIENTIFICO DISCIPLINARE IINF-05/A\, PRES
 SO IL DIPARTIMENTO DI INGEGNERIA INFORMATICA\, AUTOMATICA E GESTIONALE “AN
 TONIO RUBERTI” – FACOLTÀ DI INGEGNERIA DELL’INFORMAZIONE\, INFORMATICA E S
 TATISTICAFEDERICO FUSCO TERRA’ UN SEMINARIO PUBBLICO IN DATA 17/3/2025\, A
 LLE ORE 14:00 PRESSO L’AULA B203 DEL DIAG\, E IN COLLEGAMENTO Zoom\, link 
 alla videochiamata:https://uniroma1.zoom.us/j/81925745590?pwd=3bpMj5ch1ezL
 LGaQQeP46zX9ONhbZg.1Title: Online Learning and EconomicsAbstract It is com
 mon in economic theory to model the intrinsic uncertainty of reality with 
 random variables whose laws are perfectly and publicly known. However\, pr
 actical applications often call for a more realistic and data-driven appro
 ach\, as the relevant features of the problem at hand must be obtained on 
 the field. The online learning framework provides a natural step in this d
 irection\, where no initial information is assumed\, and data is collected
  online by repeatedly interacting with the environment. Online learning is
  particularly suited for economic applications as it captures the explorat
 ion-exploitation tradeoff and the intriguing feedback models that may natu
 rally arise. This talk surveys recent works on online learning and economi
 cs\, focusing on bidding and auction design. The goal is to provide a pers
 pective on the technical challenges faced in designing and analyzing learn
 ing algorithms and to offer the tools to address them. Part of the talk is
  devoted to the construction of “hard instances” as a way of proving tight
 ness results. The talk is partly based on the recent papers “The Role of T
 ransparency in Repeated First-Price Auctions with Unknown Valuations” (STO
 C 24)\, “No-Regret Learning in Bilateral Trade via Global Budget Balance” 
 (STOC 24)\, and “Selling Joint Ads: A Regret Minimization Perspective” (EC
  24).Short Bio Federico Fusco is an RTDA at the Department of Computer\, C
 ontrol\, and Management Engineering at Sapienza University of Rome. Previo
 usly\, he was a PostDoc and completed his PhD under the supervision of Ste
 fano Leonardi in the same institution. During his Ph.D.\, he was hosted by
  Paul Duetting at Google Research Zurich as a research intern and then as 
 a student researcher. Federico's research interests span Algorithmic Game 
 Theory\, Online Learning\, and Submodular Maximization.
DTSTART;TZID=Europe/Paris:20250312T131500
DTEND;TZID=Europe/Paris:20250312T131500
LAST-MODIFIED:20250312T201431Z
LOCATION:DIAG - Sapienza\, Aula B203
SUMMARY:Seminario Pubblico di Federico Fusco  - Federico Fusco \n\n\n  \n  
 \n\n    \n\n\nFederico\n\n\nFusco  \n\n  \n\n    \n\n\n\n\n\nRicercatore\n
 \n\npagina personale\n\nstanza: \n\nB115\n\ntelefono: \n\n+39 0677274087  
 \n\n  \n\n    \n\nInteressi di ricerca: \n\nStochastic Optimization\;\nAlg
 orithmic Game Theory\;\nMulti-Armed Bandits.\n\n\nqualifica_rr: \n\nAssist
 ant professors (ricercatori)
URL;TYPE=URI:https://www.diag.uniroma1.it/node/28685
END:VEVENT
END:VCALENDAR