Accepted paper @ NeurIPS 2019

Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks Gaël Letarte, Pascal Germain, Benjamin Guedj, François Laviolette Conference on Neural Information Processing Systems (NeurIPS), 2019 [pdf]   and also a communication in a workshop: Interpreting Neural Networks as Majority Votes through the PAC-Bayesian Theory Paul Viallard ; Rémi Emonet ; Pascal…

Continue reading

Kick-Off Meeting

Monday, 27th May – Inria, Paris Attendees: Rémi Emonet, Léo Gautheron, Pascal Germain, Benjamin Guedj, Amaury Habrard, Vera Shalaeva, Emilie Morvant, Paul Viallard Scientific talks Vera Shalaeva, PAC-Bayesian Generalization Bounds For Dropout Neural Networks Paul Viallard, Interpreting Neural Networks as Majority Votes Pascal Germain, Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep…

Continue reading

Accepted paper @ AISTATS 2019

Pseudo-Bayesian Learning with Kernel Fourier Transform as Prior Gaël Letarte ; Emilie Morvant ; Pascal Germain International Conference on Artificial Intelligence and Statistics (AISTATS), 2019, Naha, Okinawa, Japan The pre-publication document available as research report arXiv:1810.12683

Continue reading