Alex Gilotte, researcher at the Criteo AI Lab, details how counterfactual reasoning may be applied to evaluate a recommender system. The first posts introduce the topic and the intuitions behind the mathematics of counterfactual reasoning, and the later...
What defines large-scale machine learning? This seemingly innocent question is often answered with petabytes of data and hundreds of GPUs. It turns out that large-scale machine learning does not have much to do with all of that. In...
The paper on “A Principle of Least Action for the Training of Neural Networks” by Skander Karkar, Patrick Gallinari and their LIP6_lab co-authors, has been selected as the best student ML paper award Runner-up @ECMLPKDD! https://bit.ly/3gL19qA
The Reco team has released DeepR, a package to train deep recommendation models in production! See the full post here, with links to Github, docs, quick start guide and some examples: DeepR on Medium.
One paper accepted at ECCV2020! “Do not mask what you do not need to mask: a parser free Virtual Try-on” Authors: T. Issenhuth (Criteo AI Lab), J. Mary (Criteo AI Lab), C. Calauzènes (Criteo AI Lab)
One paper accepted at ECML 2020: A Principle of Least Action for the Training of Neural Networks Authors. Skander Karkar (LIP6, Sorbonne Université / Criteo AI Lab), Ibrahim Ayed (LIP6, Sorbonne Université), Emmanuel de Bézenac (LIP6, Sorbonne Université),...
We are happy to have 9 papers co-authored by members of the Criteo AI Lab getting in ICML 2020: Gradient-free Online Learning in Continuous Games with Delayed Rewards, A. Héliou, P. Mertikopoulos, and Z. Zhou. Finite-Time Last-Iterate Convergence...
Two papers co-authored by Vianney Perchet, researcher at Criteo AI Lab, got accepted at COLT 2020 Selfish Robustness and Equilibria in Multi-Player Bandits, E. Boursier, V. Perchet. https://arxiv.org/abs/2002.01197 Covariance-adapting algorithm for semi-bandits with application to sparse rewards, P....
Two papers co-authored by Criteo AI Lab researchers and their colleagues accepted at KDD 2020! Paper #1: Joint Policy-Value Learning for Recommendation Authors: Olivier Jeunen(intern), David Rohde, Flavian Vasile. Martin Bompaire Abstract. Conventional approaches to recommendation often do...
Our REVEAL workshop about Bandit and RL for user interactions will be held at RecSys’20. Co-organizers: Maria Dimakopoulou (Netflix), Thorsten Joachims (Cornell), Olivier Koch (Criteo AI Lab), Yves Raimond (Netflix)Adith Swaminathan (Microsoft), and Flavian Vasile (Crite AI Lab)....
