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:20231029T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RDATE:20241027T030000
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240331T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.28054.field_data.0@www.u-gov-ricerca.uniroma1.it
DTSTAMP:20260405T115538Z
CREATED:20240416T151939Z
DESCRIPTION:AbstractSubmodular functions are used to characterize the dimin
 ishing-returns property\, which appears in many application areas\, includ
 ing information summarization\, sensor placement\, viral marketing\, and m
 ore. Optimizing submodular functions has a rich history in mathematics and
  operations research\, while recently\, the subject has received increased
  attention due to the prevalent role of submodular functions in a broad ra
 nge of data-science applications. In this talk we will discuss two recent 
 projects on the topic of interpretable classification\, both of which make
  interesting connections with submodular optimization. For the first proje
 ct\, we address the problem of multi-label classification via concise and 
 discriminative rule sets. Submodularity is used to account for diversity\,
  which helps avoiding redundancy\, and thus\, controlling the number of ru
 les in the solution set. In the second project we aim to find accurate dec
 ision trees that have small size\, and thus\, are interpretable. We study 
 a general family of impurity functions\, including the popular functions o
 f entropy and Gini-index\, and show that a simple enhancement\, relying on
  the framework of adaptive submodular ranking\, can be used to obtain a lo
 garithmic approximation guarantee on the tree complexity.BioAristides Gion
 is is a WASP professor in KTH Royal Institute of Technology\, Sweden\, and
  an adjunct professor in Aalto University\, Finland. He obtained his PhD f
 rom Stanford University\, USA\, and he has been a senior research scientis
 t in Yahoo! Research. He has contributed in several areas of data science\
 , such as data clustering and summarization\, graph mining and social-netw
 ork analysis\, analysis of data streams\, and privacy-preserving data mini
 ng. His current research is funded by the Wallenberg AI\, Autonomous Syste
 ms and Software Program (WASP) and by the European Commission with an ERC 
 Advanced grant (REBOUND) and the project SoBigData++.
DTSTART;TZID=Europe/Paris:20240423T120000
DTEND;TZID=Europe/Paris:20240423T120000
LAST-MODIFIED:20240416T160253Z
LOCATION:Aula Magna\, Via Ariosto 25
SUMMARY:Submodular optimization and interpretable machine learning  - Arist
 ides Gionis\, KTH Royal Institute of Technology\, Sweden
URL;TYPE=URI:http://www.u-gov-ricerca.uniroma1.it/node/28054
END:VEVENT
END:VCALENDAR