Arnaud Pannatier

Fran├žois Fleuret's Machine Learning Group
Office: CP306-14
Publications: Google Scholar account: _42_
My way to Compostela:

About me

Hi ! I'm Arnaud. I started my PhD in Fran├žois Fleuret's Machine Learning group in March 2020. I am trying to forecast wind at high-altitude based on live data. Current forecasts given by National Weather agencies are too sparse in time and space to be reliable to manage air traffic. We are trying to solve that problem by nowcast the wind based on the last aircraft's measurements. Our first work on that task introduced a GPU-accelerated kernel method. In our second work, we tried a transformer-based approach and managed to increase the accuracy of our model.

I worked recently on HyperMixer, which is based on Florian Mai's idea to use hypernetworks to enable MLPMixer to handle various length inputs. This allowed the model to handle inputs in a permutation-invariant manner, and we showed that it gave the model a kind of attention behavior which scales linearly with the input length.

I made a Bachelor in Physics followed by a Master in Computer Sciences and Engineering (CSE - MATH), both at EPFL. I recieved the Kudelski Award for my Master Thesis A control plane in time and space for locality preserving blockchains in the Decentralized Distributed Systems Laboratory .


A. Pannatier, K. Matoba, F. Fleuret Attention-based Modeling of Physical Systems: Improved Latent Representations.

F. Mai, A. Pannatier, F. Fehr, H. Chen, F. Marelli, F. Fleuret, J. Henderson HyperMixer: An MLP-based Low Cost Alternative to Transformers. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2023.
publication / arxiv

A. Pannatier, R. Picatoste, and F. Fleuret. Efficient Wind Speed Nowcasting with GPU-Accelerated Nearest Neighbors Algorithm. In Proceedings of the SIAM International Conference on Data Mining (SDM), 2022.
publication / arxiv / slides