Alexandre Araujo

alexandre.araujoinria.fr

Last update May 2022

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.
Google Scholar
Resume
Research
Towards Evading the Limits of Randomized Smoothing: A Theoretical Analysis
R. Ettedgui*, A. Araujo*, R. Pinot, Y. Chevaleyre and J. Atif
Under review • 2022
paper • bibtex
A Dynamical System Perspective for Lipschitz Neural Networks
L. Meunier*, B. Delattre*, A. Araujo* and A. Allauzen
ICML • 2022 — ORAL
paper • bibtex
Building Compact and Robust Deep Neural Networks with Toeplitz Matrices
A. Araujo
PhD Thesis • 2021
paper • bibtex
On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory
A. Araujo, B. Negrevergne, Y. Chevaleyre and J. Atif
AAAI • 2020
paper • code • bibtex
Advocating for Multiple Defense Strategies against Adversarial Examples
A. Araujo, L. Menuier, R. Pinot and B. Negrevergne
ECML - Workshops • 2020
paper • bibtex
Theoretical Evidence for Adversarial Robustness through Randomization
R. Pinot, L. Meunier, A. Araujo, H. Kashima, F. Yger, C. Gouy-Pailler and J. Atif
NeurIPS • 2019
paper • code • bibtex
Understanding and Training Deep Diagonal Circulant Neural Networks
A. Araujo, B. Negrevergne, Y. Chevaleyre and J. Atif
ECAI • 2019
paper • bibtex
Training Compact Deep Learning Models for Video Classification using Circulant Matrices
A. Araujo, B. Negrevergne, Y. Chevaleyre and J. Atif
ECCV - Workshops • 2018
paper • code • bibtex