Choisir la langue :

M. Perrot (MPI): Comparison-Based Learning: Hierarchical Clustering and Classification

Institutional tag: 
Thematic tag(s): 

We address the problem of learning in a framework where one does not have access to a representation of the examples nor to their pairwise similarities. Instead, we assume that only a set of comparisons between objects is available. These comparisons are statements of the form ``objects A and B are more similar than objects C and D'' or ``object A is more similar to object B than to object C.'' Such a scenario is commonly encountered in crowdsourcing applications.
In this talk, we study the problems of hierarchical clustering and classification in such a comparison-based framework. In both cases, we propose new algorithms that are able to directly learn from the comparisons and come with theoretical guarantees on their performances.

Friday, November 22, 2019 - 14:00 to 15:00
Inria B21
Michaël Perrot
Max Planck Institute for Intelligent Systems