%0 Conference Proceedings %T Systematics aware learning: a case study in High Energy Physics %+ TAckling the Underspecified (TAU) %+ Laboratoire de l'Accélérateur Linéaire (LAL) %A Estrade, Victor %A Germain, Cécile %A Guyon, Isabelle %A Rousseau, David %< avec comité de lecture %B ESANN 2018 - 26th European Symposium on Artificial Neural Networks %C Bruges, Belgium %8 2018-04-25 %D 2018 %Z Statistics [stat]/Machine Learning [stat.ML]Conference papers %X Experimental science often has to cope with systematic errors that coherently bias data. We analyze this issue on the analysis of data produced by experiments of the Large Hadron Collider at CERN as a case of supervised domain adaptation. Systematics-aware learning should create an efficient representation that is insensitive to perturbations induced by the systematic effects. We present an experimental comparison of the adversarial knowledge-free approach and a less data-intensive alternative. %G English %2 https://inria.hal.science/hal-01715155/document %2 https://inria.hal.science/hal-01715155/file/systematics-aware-learning.pdf %L hal-01715155 %U https://inria.hal.science/hal-01715155 %~ IN2P3 %~ LAL %~ CNRS %~ INRIA %~ UNIV-PSUD %~ INRIA-SACLAY %~ INRIA_TEST %~ TESTALAIN1 %~ UMR8623 %~ CENTRALESUPELEC %~ INRIA2 %~ LRI-AO %~ UNIV-PARIS-SACLAY %~ UNIV-PSUD-SACLAY %~ INRIA-SACLAY-2015 %~ CENTRALESUPELEC-SACLAY %~ LISN %~ GS-ENGINEERING %~ GS-COMPUTER-SCIENCE %~ LISN-AO