9 papers accepted to @NeurIPS20 co-authored by researchers from Criteo AI Lab

By: Criteo AI Lab / 01 Oct 2020

We are happy to have 9 papers co-authored by researchers from the Criteo AI Lab at NeurIPS 2020

  • Online non-convex optimization with inexact models, A. Héliou, M. Martin, P. Mertikopoulos, and T. Rahier
  • Explore aggressively, update conservatively: Stochastic extragradient methods with variable stepsize scaling. Y. G. Hsieh, F. Iutzeler, and J. Malick, P. Mertikopoulos
  • No-regret learning and mixed Nash equilibria: They do not mix. L. Flokas, E. V. Vlatakis-Gkaragkounis, T. Lianeas, P. Mertikopoulos, G. Piliouras
  • On the almost sure convergence of stochastic gradient descent in non-convex problems, P. Mertikopoulos, N. Hallak, A. Kavis, V. Cevher
  • On the Convergence of Smooth Regularized Approximate Value-Iteration Schemes, E. Smirnova and E. Dohmatob
  • Statistical Efficiency of Thompson Sampling for Combinatorial Semi-Bandits, P. Perrault, E. Boursier, M. Valko and V. Perchet
  • Robustness of Community Detection to Random Geometric Perturbations, S. Péché and V. Perchet
  • Normalizing Kalman Filters for Multivariate Time Series Analysis, E. de Bézenac, S. S. Rangapuram, K. Benidis, M. Bohlke-Schneider, L. Stella, H. Hasson, R. Kurle, T. Januschowski, P. Gallinari
  • On ranking via sorting by estimated expected utility. C. Calauzènes, N. Usunier