Comparison-Based Random Forests

schedule le mardi 03 juillet 2018 de 10h45 à 11h45

Organisé par : Castillo, Fischer, Giulini, Gribkova, Levrard, Roquain, Sangnier

Intervenant : Damien Garreau (Max Planck Institute)
Lieu : UPMC, salle 15-16.201

Sujet : WHInter: A Working set algorithm for High-dimensional sparse second order Interaction models

Résumé :

Assume we are given a set of items from a general metric space, but we neither have access to the representation of the data nor to the distances between data points. Instead, suppose that we can actively choose a triplet of items (A,B,C) and ask an oracle whether item A is closer to item B or to item C. In this talk, I will present a novel random forest algorithm for regression and classification that relies only on such triplet comparisons. The related paper is available at https://arxiv.org/abs/1806.06616.