Nine research papers coauthored by CREST members accepted at NeurIPS 2021 Conference:

https://www.hi-paris.fr/2021/12/03/hi-paris-at-neurips-2021/

– Stochastic Online Linear Regression: the Forward Algorithm to Replace Ridge
Reda Ouhamma · Odalric-Ambrym Maillard · Vianney Perchet

– Decentralized Learning in Online Queuing Systems
Flore Sentenac · Etienne Boursier · Vianney Perchet

– Online Matching in Sparse Random Graphs: Non-Asymptotic Performances of Greedy Algorithm
Nathan Noiry · Vianney Perchet · Flore Sentenac

– Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits
Reda Ouhamma · Rémy Degenne · Vianney Perchet · Pierre Gaillard

– Making the most of your day: online learning for optimal allocation of time
Etienne Boursier · Tristan Garrec · Vianney Perchet · Marco Scarsini

– A New Theoretical Framework for Fast and Accurate Online Decision-Making
Nicolò Cesa-Bianchi · Tom Cesari · Yishay Mansour · Vianney Perchet

– Local Differential Privacy for Regret Minimization in Reinforcement Learning
Evrard Garcelon · Vianney Perchet · Ciara Pike-Burke · Matteo Pirotta

– Distributed Zero-Order Optimization under Adversarial Noise
Arya Akhavanfoomani · Massimiliano Pontil · Alexandre Tsybakov

– Locally differentially private estimation of functionals of discrete distributions
Cristina Butucea · Yann Issartel