CRITEO DATA TERMS OF USE FOR MLPERF Users By exercising the Licensed Rights (defined below), You accept and agree to be bound by the terms and conditions of this Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License (“Public License”)....
A few papers co-authored by Criteos recently accepted at many premiere ML venues! Congrats to all and their co-authors. EC 2022 Vianney Perchet, Philippe Rigollet, Thibaut Le Gouic, ”An algorithmic solution to the Blotto game using multi-marginal couplings”,...
Foundation and Trends in ML: Learning in repeated auctions (Foundation and Trends in ML) – Thomas Nedelec, Clément Calauzènes, Noureddine El Karoui, Vianney Perchet, https://arxiv.org/abs/2011.09365 JMLR Multi-Agent Online Optimization with Delays: Asynchronicity, Adaptivity, and Optimism With Yu-Guan Hsieh,...
We are proud to see people from the AI Lab co-authors of 13 papers at NeurIPS (affiliations and order of authors to be adjusted soon): Photonic Differential Privacy with Direct Feedback Alignment, Ruben Ohana (LightOn), H.-J Medina Ruiz...
3 papers from Criteo AI Lab folks made the cut at KDD21 (International Conference on Knowledge Discovery & Data Mining): Uplift Modeling with Generalization Guarantees, A. Betlei (Criteo AI Lab), E. Diemert (Criteo AI Lab), M.-R. Amini (LIG/UGA) Individual...
3 papers from Criteo AI Lab folks at COLT 21: The last-iterate convergence rate of optimistic mirror descent in stochastic variational inequalities, W. Azizian (ENS), F. Iutzeler (UGA), J. Malick (CNRS), and P. Mertikopoulos (Criteo AI Lab/CNRS) Survival...
6 papers from the Criteo AI Lab at ICML 21: Online A-Optimal Design and Active Linear Regression, X. Fontaine (ENS Paris), P. Perrault (ENS Paris), V. Perchet (Criteo AI Lab / ENSAE), M. Valko (Deepmind) Pure Exploration and Regret Minimization...
The Online Advertising industry is seeing a major shift today in its operational constraints with a global movement towards more privacy. Popular techniques for privacy-compliant advertising such as aggregation and differential privacy mechanisms were shown to match high privacy standards...
A Workshop organized by people from the Criteo AI Lab at KDD 2021 Summary. Machine learning has allowed many systems that we interact with to improve performance and personalize. An important source of information in these systems is to...
We are pleased to announce a privacy-preserving learning challenge at CAp’21. The goal is to find a representation of a stream of events (x) such that a prediction (y) task is possible while being able to detect that...
