2000 character limit reached
Concentration Inequalities for Bounded Random Vectors (1309.0003v1)
Published 30 Aug 2013 in math.PR, cs.LG, math.ST, and stat.TH
Abstract: We derive simple concentration inequalities for bounded random vectors, which generalize Hoeffding's inequalities for bounded scalar random variables. As applications, we apply the general results to multinomial and Dirichlet distributions to obtain multivariate concentration inequalities.