Jean-Baptiste Cordonnier

jean-baptiste.cordonnier@epfl.ch Profile picture

I am a PhD candidate at EPFL supervised by Prof. Martin Jaggi in the Machine Learning and Optimization lab. I work closely with Andreas Loukas on graph related topics. I received my Bachelor and Master degrees in Communication Systems at EPFL.

My research interests include unsupervised knowledge extraction, graph neural networks, natural language processing and distributed optimization.

Publications

Extrapolating paths with graph neural networks, Jean-Baptiste Cordonnier and Andreas Loukas.
IJCAI'19 • PDFCodeBibTex @article{DBLP:journals/corr/abs-1903-07518, author = {Jean{-}Baptiste Cordonnier and Andreas Loukas}, title = {Extrapolating paths with graph neural networks}, journal = {CoRR}, volume = {abs/1903.07518}, year = {2019} }

Sparsified SGD with Memory, Sebastian U. Stich, Jean-Baptiste Cordonnier and Martin Jaggi.
NeurIPS '18 • PDFPosterCodeBibTex @inproceedings{DBLP:conf/nips/StichCJ18, author = {Sebastian U. Stich and Jean{-}Baptiste Cordonnier and Martin Jaggi}, title = {Sparsified {SGD} with Memory}, booktitle = {NeurIPS}, pages = {4452--4463}, year = {2018} }

Convex Optimization using Sparsified SGD with Memory, Jean-Baptiste Cordonnier.
Master thesis EPFL • PDFBibTex @article{Cordonnier:262760, title = {Convex Optimization using Sparsified Stochastic Gradient Descent with Memory}, author = {Cordonnier, Jean-Baptiste}, pages = {49 pages}, year = {2018}, url = {http://infoscience.epfl.ch/record/262760}, }

Avalanche risk analysis, Jean-Baptiste Cordonnier, Brune Bastide and Arnaud Lesimple.
AMLD '18 • Website
Best project award in Applied Data Analysis course

Contact me

You can consult my CV or check out my activity on Github and my LinkedIn profile. Don't hesitate to drop me an email.