s'authentifier
version française rss feed
HAL : hal-00643001, version 1

Voir la fiche détaillée  BibTeX,EndNote,...
Yahoo! Learning to Rank Challenge, Haifa : Israël (2010)
Ranking by calibrated AdaBoost
Róbert Busa-Fekete1, Balázs Kégl1, 2, 3, Tamas Elteto3, György Szarvas4
(15/06/2011)

This paper describes the ideas and methodologies that we used in the Yahoo learning-to- rank challenge1. Our technique is essentially pointwise with a listwise touch at the last combination step. The main ingredients of our approach are 1) preprocessing (querywise normalization) 2) multi-class AdaBoost.MH 3) regression calibration, and 4) an expo- nentially weighted forecaster for model combination. In post-challenge analysis we found that preprocessing and training AdaBoost with a wide variety of hyperparameters im- proved individual models significantly, the final listwise ensemble step was crucial, whereas calibration helped only in creating diversity.
1 :  LAL - Laboratoire de l'Accélérateur Linéaire
2 :  LRI - Laboratoire de Recherche en Informatique
3 :  INRIA Saclay - Ile de France - TAO
4 :  Ubiquitous Knowledge Processing (UKP) Lab
Informatique/Apprentissage
Liste des fichiers attachés à ce document :
PDF
final.pdf(221.7 KB)