Alexandre Araujo

alexandre.araujoinria.fr

Last update October 2021

I am currently a postdoctoral researcher at INRIA and École Normale Supérieure (ENS) in the WILLOW project-team in Paris, France. I work with Jean Ponce and Julien Mairal (INRIA Grenoble) on Computer Vision and Machine Learning. I obtained my PhD in Computer Science in June 2021 at Université Paris Dauphine-PSL where I was advised by Pr. Jamal Atif, Pr. Yann Chevaleyre and Dr. Benjamin Negrevergne. During my PhD, I have focused on how to leverage the properties of structured matrices to improve the training of neural networks.
Research
Building Compact and Robust Deep Neural Networks with Toeplitz Matrices
Alexandre Araujo
PhD Thesis • 2021
paperbibtex
On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory
Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre and Jamal Atif
AAAI • 2020
papercodebibtex
Advocating for Multiple Defense Strategies against Adversarial Examples
Alexandre Araujo, Laurent Menuier, Rafael Pinot and Benjamin Negrevergne
ECML - Workshops • 2020
paperbibtex
Theoretical Evidence for Adversarial Robustness through Randomization
Rafael Pinot, Laurent Meunier, Alexandre Araujo, Hisashi Kashima, Florian Yger, Cédric Gouy-Pailler and Jamal Atif
NeurIPS • 2019
papercodebibtex
Understanding and Training Deep Diagonal Circulant Neural Networks
Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre and Jamal Atif
ECAI • 2019
paperbibtex
Training Compact Deep Learning Models for Video Classification using Circulant Matrices
Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre and Jamal Atif
ECCV - Workshops • 2018
papercodebibtex