2 code implementations • NeurIPS 2023 • Darko Drakulic, Sofia Michel, Florian Mai, Arnaud Sors, Jean-Marc Andreoli
In this paper, we present a novel formulation of Combinatorial Optimization Problems (COPs) as Markov Decision Processes (MDPs) that effectively leverages common symmetries of COPs to improve out-of-distribution robustness.
Combinatorial Optimization Out-of-Distribution Generalization
no code implementations • 20 Dec 2021 • Sarah Ibrahimi, Arnaud Sors, Rafael Sampaio de Rezende, Stéphane Clinchant
Learning with noisy labels is an active research area for image classification.
no code implementations • 27 Sep 2018 • Morgan Funtowicz, Tomi Silander, Arnaud Sors, Julien Perez
More precisely, our forward model is trained to produce realistic observations of the future while a discriminator model is trained to distinguish between real images and the model’s prediction of the future.