Max-Planck-Institut für Informatik
max planck institut
informatik
mpii logo Minerva of the Max Planck Society
 

MPI-INF or MPI-SWS or Local Campus Event Calendar

<< Previous Entry Next Entry >> New Event Entry Edit this Entry Login to DB (to update, delete)
What and Who
Title:Extreme Classification: Algorithms and Theory
Speaker:Marius Kloft
coming from:TU Kaiserslautern
Speakers Bio:
Event Type:Talk
Visibility:D1, D2, D3, D4, D5, RG1, SWS, MMCI
We use this to send out email in the morning.
Level:Public Audience
Language:English
Date, Time and Location
Date:Tuesday, 12 June 2018
Time:12:00
Duration:60 Minutes
Location:Saarbr├╝cken
Building:E1 5
Room:029
Abstract
In my talk, I will present novel algorithms and theory for 'extreme classification', which is multi-class (MC) classification using an *extremely* large number of label classes.

The main contributions are:
(1) Statistical generalization error bounds that scale *logarithmically* in the number of classes (previously best scaling: linear), allowing us to learn even when
#classes > #instances.
(2) Optimization algorithms that distribute the training of all-in-one multi-class SVMs over the classes, which makes them appealing for the use in extreme classification.

Contact
Name(s):Connie Balzert
Video Broadcast
Video Broadcast:NoTo Location:
Tags, Category, Keywords and additional notes
Note:
Attachments, File(s):

Created:
Connie Balzert/MPI-INF, 06/08/2018 11:49 AM
Last modified:
Uwe Brahm/MPII/DE, 06/12/2018 07:01 AM
  • Connie Balzert, 06/08/2018 11:49 AM -- Created document.