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 (Criteo), Julien Launay (LightOn), Alessandro Cappelli (LightOn), Iacopo Poli (LightOn), L. Ralaivola (Criteo), A. Rakotomamonjy (Criteo)
- 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.
- 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.
- Adaptive first-order methods revisited: Convex optimization without Lipschitz requirements, P. Mertikipoulos in a joint work with Kimon Antonakopoulos.
- 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.
- Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits, R. Ouhamma, R. Degenne, V. Perchet and P. Gaillard
- Decentralized Learning in Online Queuing Systems, F. Sentenac, E. Boursier, V. Perchet
- Stochastic Online Linear Regression: the Forward Algorithm to Replace Ridge, R. Ouhamma, O-A Maillard, V. Perchet
- Local Differential Privacy for Regret Minimization in Reinforcement Learning, E. Garcelon, V.Perchet, C. Pike-Burke, M. Pirotta
- Online Matching in Sparse Random Graphs: Non-Asymptotic Performances of Greedy Algorithm, N. Noiry, V. Perchet, F. Sentenac
- A New Theoretical Framework for Fast and Accurate Online Decision-Making, N. Cesa-Bianchi, T. Cesari, Y. Mansour, V. Perchet
- Making the most of your day: online learning for optimal allocation of time, E. Boursier, T. Garrec, V. Perchet, M. Scarsini
- 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