13 papers from CAIL folks at NeurIPS 2021

By: Criteo AI Lab / 30 Sep 2021

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):

  1. Photonic Differential Privacy with Direct Feedback Alignment, Ruben Ohana (LightOn), H.-J Medina Ruiz (Criteo), Julien Launay (LightOn), Alessandro Cappelli (LightOn), Iacopo Poli (LightOn), L. Ralaivola (Criteo), A. Rakotomamonjy (Criteo)
  2. The convergence rate of regularized learning in games: From bandits and uncertainty to optimism and beyond, P. Mertikipoulos in a joint work with Angeliki Giannou and Emmanouil Vlatakis-Gkaragkounis.
  3. Fast resource allocation under uncertainty: Adaptive learning in congestion games with exponential weights, P. Mertikipoulos in a joint work with Dong Quan Vu and Kimon Antonakopoulos.
  4. Adaptive first-order methods revisited: Convex optimization without Lipschitz requirements, P. Mertikipoulos in a joint work with Kimon Antonakopoulos.
  5. Sifting through the noise: Universal first-order methods for stochastic variational inequalities, P. Mertikipoulos in a joint work with Kimon Antonakopoulos, Thomas Pethick, Ali Kavis, and Volkan Cevher.
  6. Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits, R. Ouhamma, R. Degenne, V. Perchet and P. Gaillard
  7. Decentralized Learning in Online Queuing Systems, F. Sentenac, E. Boursier, V. Perchet
  8. Stochastic Online Linear Regression: the Forward Algorithm to Replace Ridge,  R. Ouhamma, O-A Maillard, V. Perchet
  9. Local Differential Privacy for Regret Minimization in Reinforcement Learning, E. Garcelon,  V.Perchet, C. Pike-Burke, M. Pirotta
  10. Online Matching in Sparse Random Graphs: Non-Asymptotic Performances of Greedy Algorithm, N. Noiry, V. Perchet, F. Sentenac
  11. A New Theoretical Framework for Fast and Accurate Online Decision-Making, N. Cesa-Bianchi, T. Cesari, Y. Mansour, V. Perchet
  12. Making the most of your day: online learning for optimal allocation of time, E. Boursier, T. Garrec,  V. Perchet, M. Scarsini
  13. LEADS: Learning Dynamical Systems that Generalize Across Environments, Yuan Yin, Ibrahim Ayed, Emmanuel de Bezenac, Nicolas Baskiotis, Patrick Gallinari, https://arxiv.org/abs/2106.04546