APRIORI Project – Page 2 – A PAC-Bayesian Representation Learning Perspective

Keywords of the Project

PAC-Bayesian Theory

A Statistical Machine Learning well-designed for functions that take the form of a weighted combination

APRIORI in few words

In data science, defining a meaningful data representation is often a crucial preliminary step of the data processing pipeline. The Apriori project is rooted in the sub-field of machine learning called representation learning, which overlaps many topics such as deep learning, metric learning and kernel methods. Apriori focuses on understanding and replicating the successes of those methods. While classical machine learning algorithms are supported by sound theoretical analyses and clear heuristics, representation learning is often deemed to be lacking both. The originality of the project stands in bridging the gap between the representation learning algorithms and the theory by using the PAC- Bayesian arsenal: a statistical machine learning theory that appears naturally tailored to study representation learning problems. We believe that a sound analysis of representation learning—that will also lead to new well-founded algorithms—can be a significant contribution to machine learning and representation learning practitioners.

Kick-Off Meeting

emorvant 2019/05/27 2019/05/28Meetings, News

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…

Accepted paper @ AISTATS 2019

emorvant 2019/01/09 2019/01/10Paper

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

Welcome to our website

emorvant 2019/01/09 2019/01/09News

Welcome to the website of the french project APRIORI funded by the French “Agence Nationale de la Recherche”.

A Priori Members


Rémi Emonet Assistant Professor Lab. Hubert Curien	Pascal Germain Assistant Professor GRAAL & Inria Lille - Nord Europe	Benjamin Guedj Research Scientist UCL & Inria Lille - Nord Europe	Amaury Habrard Professor Lab Hubert Curien	Emilie Morvant Assistant Professor Lab. Hubert Curien

Hemant Tyagi Research Scientist Inria Lille - Nord Europe	Léo Gautheron Post Doc Lab. Hubert Curien	Valentina Zantedeschi Post-Doc UCL & Inria Lille - Nord Europe	Paul Viallard Ph.D. Student Lab. Hubert Curien