Campus Event Calendar
Event Entry
What and Who
Extreme Classification: Algorithms and Theory
Marius Kloft
TU Kaiserslautern
Talk
AG 1, AG 2, AG 3, AG 4, AG 5, RG1, SWS, MMCI
Public Audience
English
Note: We use this to send email in the morning.
Date, Time and Location
Tuesday, 12 June 2018
12:00
60 Minutes
E1 5
029
Saarbrücken
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
Connie Balzert
--email hidden
passcode not visible
logged in users only
Connie Balzert, 06/08/2018 11:49 -- Created document.