Webpage of Edouard Oyallon
I am Edouard Oyallon, a tenure track Assistant Professor at the Centre de Vision Numérique (CVN) de CentraleSupelec. Prior to it, I was a postdoctoral research fellow at the INRIA Lille, where I worked in particular with Michal Valko. I obtained my PhD in October 2017 from the Département Informatique de l'Ecole Normale Supérieure under the supervision of Prof. Stéphane Mallat. I graduated from the ENS Cachan, campus de Ker Lann. I define myself as an applied mathematician, with coding skills.
My research interests are in the fields of computer vision, reinforcement learning and machine learning, and more generally signals that have a lot of geometric structure (text, sounds..). More precisely, I am interested in the mathematical foundations of deep learning techniques because they provide state-of-the-art results on many benchmarks. I try to interpret why such methods generalize from a training dataset to a testing dataset, by attempting to understand the underlying mechanisms to build geometrical and more complex invariants.
I hate black box pipelines, and to be concise, the type of questions I try to solve is not “how to learn new deep features that discriminate this image as a dog”, but simply “why is your network understanding that this signal is a dog”. Answering such questions could help to make fundamental advances in science in a context where too much work is dedicated to techniques that give incremental improvements on standard datasets.
Recently, I am interested in the theoritical understanding of the deep reinforcement learning techniques that have led to breakthrough results in solving strategy games such as Go.
Feel free to send me any emails to discuss my work at edouard[dot]oyallon[at]centralesupelec[dot]fr.
Feb 2018, I am grateful to have received a GPU donation from NVIDIA.
My google scholar.
Jan 1st 2018, I will join the CVN at CentraleSupelec as a tenure track Assistant Professor.
Nov 1st 2017, I will join the SequeL team at Lille, to work in particular with Michal Valko and Matteo Pirotta.
List of publications:
- Scieur, D., Oyallon, E., d'Aspremont, A. and Bach, F. - Nonlinear Acceleration of Deep Neural Networks, preprint. https://arxiv.org/abs/1805.09639
- Oyallon, E., Belilovsky, E., Zagoruyko, S., and Valko, M. - Compressing the Input for CNNs with the First-Order scattering Transform, ECCV 2018. https://arxiv.org/abs/1809.10200, poster
- Scieur, D., Oyallon, E., d'Aspremont, A. and Bach, F. - Nonlinear Acceleration of CNNs, ICLR workshop 2018. https://openreview.net/forum?id=HkNpF_kDM
- Oyallon, E., Zagoruyko, S., Huang G., Komodakis, N., Lacoste-Julien, S., Blaschko M., and Belilovsky E. - Scattering Networks for Hybrid Representation Learning, TPAMI 2018. https://arxiv.org/abs/1809.06367
- Jacobsen, J.-H., Smeulders, A.W.M. and Oyallon, E. - i-RevNet: Deep Invertible Networks, ICLR 2018. https://openreview.net/forum?id=HJsjkMb0Z
- Oyallon, E. - Analyzing and Introducing Structures in Deep Convolutional Neural Networks, "Thèse de doctorat", 2017, slides
- Oyallon, E., Belilovsky, E., and Zagoruyko, S. - Scaling the Scattering Transform: Deep Hybrid Networks, ICCV 2017. https://arxiv.org/abs/1703.08961, poster
- Jacobsen, J.-H., Oyallon, E., Mallat, S. and Smeulders, A.W.M. - Multiscale Hierarchical Convolutional Networks, ICML PADL 2017. https://arxiv.org/abs/1703.04140, poster
- Oyallon, E. - Building a Regular Decision Boundary with Deep Networks, CVPR 2017. https://arxiv.org/abs/1703.01775, poster
- Oyallon, E. - A hybrid network: Scattering and Convnet. https://openreview.net/pdf?id=ryPx38qge, reviews
- Oyallon, E. and Mallat, S. - Deep Roto-translation Scattering for Object Classification, CVPR 2015. http://arxiv.org/abs/1412.8659, poster
- Oyallon, E. and Rabin, J. - An Analysis of the SURF Method, IPOL 2015. http://www.ipol.im/pub/art/2015/69/
- Oyallon, E., Mallat, S. and Sifre, L. - Generic Deep Networks with wavelet Scattering, ICLR 2014 workshop. http://arxiv.org/abs/1312.5940, poster
- 2018, Teaching assistant, Deep Learning, MVA
- 2018, Second year seminar ENSAE, slides
- 2017, Corporate Seminar Series with lumenai
- 2017, Seminar at M2 StatML, slides
- 2017, Second year seminar ENSAE, slides
- 2014-2017, Teaching assistant, ENSAE, fundamental probability classes and calculus
- 2019, Journee Stat/ML de Paris-Saclay, IHES
- 2018, GE Healthcare, Bures-sur-Yvette
- 2018, NAVER LABS, Grenoble
- 2018, Criteo, Paris
- 2018, SequeL, Lille
- 2018, SONY CSL Music
- 2018, DeepMind CSML Seminar Series
- 2018, Mathematical coffee at Huawei
- 2018, Imaging in Paris Seminar
- 2017, GREYC, Caen
- 2017, LIP6, Paris
- 2017, cfm
- 2017, Torr Vision Group
- 2017, Paris Big Data, Télécom Paris Tech, slides.
- 2017, Leuven, seminar.
- 2017, "Groupe de travail", about deep learning, Rennes 1, invited by Adrien Saumard, slides.
- 2017, Meetup at Rennes, France.
- 2016, Meetup at Pau, France.
- 2015, Journée
DIM RDM-IDF, UPMC, Paris, talk (french).
- 2015, GREYC, Paris, slides.