BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//jEvents 2.0 for Joomla//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:0tvdfjtq0kihvbp2br6eru9uio@google.com
CATEGORIES:RTportal.ru
CREATED:20170606T092329
SUMMARY:Семинар СМиГО: Multi-Class Classification: How to Deal with Multi-class Huge Scale Problems Efficiently?
LOCATION:ИППИ РАН в 615 аудитории (6 этаж)
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:Presenter: Yuri Maximov (Skoltech, Los Alamos National Laboratory)<br/><br/
 >Title: Multi-Class Classification: How to Deal with Multi-class Huge Scale
  Problems Efficiently?<br/><br/>Annotation:<br/>> Multi-class classificatio
 n problems are motivated by a numerous applications in <br/>> informational
  retrieval, text analysis and engineering systems. Nowadays <br/>> problems
  require time and memory efficient algorithms with strong statistical <br/>
 > guarantees. In our talk we focus on a line of multi-class learning strate
 gies <br/>> proposed in a series of recent works joint with MR Amini, Z Har
 chaoui, <br/>> F. Iutzeler,  B, Joshi, I Partalas and  D Reshetova. Finally
  we illustrate the <br/>> efficiency of our algorithms on several practical
  problems arises in text analysis <br/>> and energy systems.  This event wa
 s imported from: https://rtportal.ru/index.php/kalendar-sobytij/eventdetail
 /124/-/seminar-smigo-multi-class-classification-how-to-deal-with-multi-clas
 s-huge-scale-problems-efficiently?tmpl=component
DTSTAMP:20260812T174939Z
DTSTART;TZID=Europe/Moscow:20170301T183000
DTEND;TZID=Europe/Moscow:20170301T200000
SEQUENCE:1
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR