ConceptHoeffding's inequality
Hoeffding's Inequality
Hoeffding's inequality is a classical concentration inequality in probability theory that provides an exponential upper bound on the deviation probability of sums of bounded random variables. It serves as the basis for multivariate generalizations such as McDiarmid's inequality.
Timeline (last 90 days)
Oct 16
The KL-UCB algorithm constructs confidence upper bounds based on KL divergence and, compared with algorithms such as UCB1 that are based on Hoeffding's inequality, can achieve tighter regret bounds under Bernoulli rewards.
Unverified50%