About Me
Laboratoire Hubert Curien
Data Intelligence Team
Bâtiment F, 18 Rue Professeur Benoît Lauras
42000 Saint-Étienne
E-Mail: paul.viallard@univ-st-etienne.fr
Links: GitHub
Since September 2019, I am PhD student at Hubert Curien Laboratory in the Data Intelligence Team under the supervision of Dr. Emilie Morvant, Dr. Pascal Germain and Pr. Amaury Habrard. My PhD is funded by the ANR project APRIORI. The subject is “Interpreting Representation Learning Through PAC-Bayes Theory”.
Publications
International Workshop
Not Published
Interpreting Neural Networks as Majority Votes through the PAC-Bayesian Theory
Paul Viallard ; Rémi Emonet ; Pascal Germain ; Amaury Habrard ; Emilie Morvant
NeurIPS 2019 Workshop on Machine Learning with guarantees, Vancouver, Canada.
[pdf][poster]
Research Reports
A General Framework for the Derandomization of PAC-Bayesian Bounds
Paul Viallard ; Pascal Germain ; Amaury Habrard ; Emilie Morvant
arXiv, 2021
[pdf]
A PAC-Bayes Analysis of Adversarial Robustness
Guillaume Vidot ; Paul Viallard ; Amaury Habrard ; Emilie Morvant
arXiv, 2021
[pdf]
French Conferences
Théorie PAC-Bayésienne pour l’apprentissage en deux étapes de réseaux de neurones
Paul Viallard ; Rémi Emonet ; Amaury Habrard ; Emilie Morvant; Pascal Germain
French Conference on Machine Learning (CAp), 2020
[pdf][poster][video]
Miscellaneous
Interpreting Neural Networks as Majority Votes with the PAC-Bayesian Theory
Paul Viallard
Master Thesis, 2019
[pdf][slides]
Talks
Nov 27th, 2020: La pop culture dans l’oeil des expert·es !
Nuit Européenne des Chercheur·e·s 2020, Saint-Etienne
[video]
Teaching
Fall 2020 (In French)
- CM - L1 - Introduction à l’informatique (6h)
- TP - L1 - Outils Numériques (16h)
- CM - L2 - Programmation Impérative (spécifique alternance) (2h)
Spring 2021 (In French)
- TP - L2 - Programmation Impérative (18h)
- TP - L1 - Outils Informatiques (14h)
- CM/TD - L2 - Système d’exploitation (16h)