Fabien Panloup, Sofiane Saadane, and Sébastien Gadat, “Regret bound for Narendra-Shapiro bandit algorithms”, Stochastics, May 2018, pp. 886–926.
Sébastien Gadat, Fabien Panloup, and Sofiane Saadane, “Stochastic Heavy Ball”, Electronic Journal of Statistics, vol. 12, n. 1, 2018, pp. 461–529.