We extend the adversarial/non-stochastic multi-play multi-armed bandit (MPMAB) to the case where the number of arms to play is variable.
In this paper we propose a novel observer-based method to improve the safety and security of connected and automated vehicle (CAV) transportation.
Integrating both numerical algorithms and advanced techniques together, TECU is proposed in a unified framework for solving a class of non-convex problems.
Enhancing visual qualities of images plays very important roles in various vision and learning applications.
In recent years, numerous vision and learning tasks have been (re)formulated as nonconvex and nonsmooth programmings(NNPs).