CONTARDO Gabriella

PhD graduated
Team : MLIA
Departure date : 09/30/2017
Supervision : Ludovic DENOYER
Co-supervision : ARTIÈRES Thierry

Machine learning under budget constraints

This thesis studies the problem of machine learning under budget constraints. More specifically, we propose to focus on the cost of the information used by the system to predict accurately. Most methods in machine learning usually defines the quality of a model as the performance (e.g accuracy) on the task at hand, but ignores the cost of the model itself: for instance, the number of examples and/or labels needed during learning, the memory used, or the number of features required to predict at test-time. We propose in this manuscript several methods for cost-sensitive prediction w.r.t. the quantity of features used. The goal is to define models that learn to interact with the examples in order to optimize a trade-off between a good prediction and a low features' acquisition cost. We present three models that learn to predict under such constraint. The first model is a static approach applied to cold-start recommendation, where the subset of features to acquire is the same for all examples. We then define two adaptive methods that adapt their acquisition strategy depending on what is currently known about the example to classify, thus allowing for a better trade-off between accuracy and features' cost. We rely on representation learning techniques with recurrent neural networks architectures. In the last part of the thesis, we propose to study the problem of active-learning, where one aims at constraining the amount of labels used to train a model. We present our work for a novel approach of the problem using meta-learning, with an instantiation based on bi-directional recurrent neural networks.
Defence : 07/10/2017 - 14h - Site Jussieu 26-00/101
Jury members :
M. Olivier Pietquin - Deepmind/Université de Lille 1 [Rapporteur]
M. Marc Sebban - Université Jean Monnet, Saint-Etienne [Rapporteur]
Mme. Anne Doucet - Université Pierre et Marie Curie, Paris
M. Balázs Kégl - Université Paris Sud 11
M. Nicolas Usunier - Facebook AI Research Paris
M. Thierry Artieres - Université Aix-Marseille
M. Ludovic Denoyer - Université Pierre et Marie Curie, Paris

2014-2018 Publications

 Mentions légales
Site map |