Learning by stochastic serializations

Rapport Rapport technique Learning by stochastic serializations eng 2019 author Strasser Pablo Ramon 635973 author Armand Stéphane 0000-0001-9144-4982 636265 author Marchand-Maillet Stéphane 0000-0002-4875-6101 518563 author Kalousis Alexandros 514211 Complex structures are typical in machine learning. Tailoring learning algorithms for every structure requires an effort that may be saved by defining a generic learning procedure adaptive to any complex structure. In this paper, we propose to map any complex structure onto a generic form, called serialization, over which we can apply any sequence-based density estimator. We then show how to transfer the learned density back onto the space of original structures. To expose the learning procedure to the structural particularities of the original structures, we take care that the serializations reflect accurately the structures' properties. Enumerating all serializations is infeasible. We propose an effective way to sample representative serializations from the complete set of serializations which preserves the statistics of the complete set. Our method is competitive or better than state of the art learning algorithms that have been specifically designed for given structures. In addition, since the serialization involves sampling from a combinatorial process it provides considerable protection from overfitting, which we clearly demonstrate on a number of experiments. Dewey 025.063 Dewey 617 13 Centre universitaire d'informatique 0D3 32 Département d'informatique 18 57 Département de chirurgie 222 false 895 Computer Vision and Multimedia Laboratory 900 Laboratoire de cinésiologie 943 675 Viper group 68495c78-1499-4c1e-81e6-89b4232ae179 Report Public 2019Strasser_learning_stochastic.pdf 3481468 application/pdf openAccess Centres et instituts / Centre universitaire d'informatique Faculté des sciences / Département d'informatique Faculté de médecine / Section de médecine clinique / Département de chirurgie

Title	Published in	Access level	OA Policy	Year	Views	Downloads

Learning by stochastic serializations				2019	302	96

Archive ouverte UNIGE

Strasser, Pablo Ramon