Alix Lhéritier

Computer Scientist. Machine Learning Researcher at Amadeus. 🚧🇺🇾🇫🇷

[Alix Lhéritier @AlixLheritier]

@ECMLPKDD Submissions appear to be closed on CMT--- one hour before the deadline according to https://t.co/qJzaRHwI0K

[federico lecumberry @flecumberry]

Everything is ready for launching @Khipu_AI tomorrow. A whole week of Artificial Intelligence in Latin America/for Latin America. You can follow all the talks in our YouTube channel 👉 https://t.co/9HvjXa3NIK

[Alix Lhéritier @AlixLheritier]

@thegautamkamath Since the already done reviews could help the authors to improve the paper for future submissions, is it possible and ok to submit the reviews or post them in some way in openreview?

[Alix Lhéritier @AlixLheritier]

We propose a low-complexity algorithm to compute the Cramér distance and show competitive experimental results on Atari games. Code: https://t.co/4V4x0arbCH based on DQN Zoo @johnquan_ @georgostrovski

[Alix Lhéritier @AlixLheritier]

Happy to share our @Aistats2020 paper "A Cramér Distance perspective on Quantile Regression based Distributional Reinforcement Learning" with
@nicolas_bondoux: https://t.co/0SJBUKeAff.
We prove novel results connecting Cramér distance to QR loss and 1-Wasserstein projection.

[Alix Lhéritier @AlixLheritier]

URGENT: @inria_sophia and @AmadeusNice propose a #postdoc "Detection of fake identity for face recognition system"
Start: 1-Mar-22
Location: #SophiaAntipolis, France
Duration: 1 year
Contact: mourad.boudia at https://t.co/UDdq2zCgVM, antitza.dantcheva at https://t.co/0eHsIyWR8p

[Alix Lhéritier @AlixLheritier]

@CamiloCerchiari @maria_miraldo Excelente Camilo! A transpirar esas camisetas!

[Andreas Madsen @andreas_madsen]

Yes! I got my first big conference paper accepted at ICLR, with spotlight! We improve the previous DeepMind paper "NALU" by 3x-20x. – This took 7-8 months, working without any funding as an independent researcher. Paper: https://t.co/DHBvwUbnMX Code: https://t.co/5ZxC47ndJu

[Alix Lhéritier @AlixLheritier]

Happy to announce that my paper on PCMC-Net has been accepted for @iclr_conf #ICLR2020!

PCMC-Net is a NN architecture representing feature-based non-linear choice models, allowing to represent context effects like the #decoyeffect.

Paper: https://t.co/qgkEel8yK6

[Alix Lhéritier @AlixLheritier]

Excited to present "Low-Complexity Nonparametric Bayesian Online Prediction with Universal Guarantees" at #NeurIPS2019!

The kd-switch universal predictor allows nonparametric scale learning with a low-complexity online algorithm.

with F. Cazals.

Code: https://t.co/IqBYH4yIz5