Timezone: »

Comparison-Based Random Forests
Siavash Haghiri · Damien Garreau · Ulrike von Luxburg

Fri Jul 13 09:15 AM -- 12:00 PM (PDT) @ Hall B #73

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 paper, we propose a novel random forest algorithm for regression and classification that relies only on such triplet comparisons. In the theory part of this paper, we establish sufficient conditions for the consistency of such a forest. In a set of comprehensive experiments, we then demonstrate that the proposed random forest is efficient both for classification and regression. In particular, it is even competitive with other methods that have direct access to the metric representation of the data.

Author Information

Siavash Haghiri (University of Tübingen)
Damien Garreau (Max Planck Institute)
Ulrike von Luxburg (University of Tübingen)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors