Lecture 7 - 8 : Martingales and Azuma ’ s inequality CSE 525 , Winter 2015
نویسنده
چکیده
We have seen that if X X1 + · · · + Xn is a sum of independent {0, 1} random variables, then X is tightly concentrated around its expected value [X]. The fact that the random variables were {0, 1}-valued was not essential; similar concentration results hold if we simply assume that they are in some bounded range [−L, L]. One can also relax the independence assumption, as we will see next. Consider a sequence of random variables X0 ,X1 ,X2 , . . .. The sequence {Xi} is called a discretetime martingale if it holds that [Xi+1 | X0 ,X1 , . . . ,Xi] Xi
منابع مشابه
On Concentration and Revisited Large Deviations Analysis of Binary Hypothesis Testing
This paper first introduces a refined version of the Azuma-Hoeffding inequality for discrete-parameter martingales with uniformly bounded jumps. The refined inequality is used to revisit the large deviations analysis of binary hypothesis testing.
متن کاملLecture 7-8: Martingales and Azuma's Inequality
We have seen that if X X1 + · · · + Xn is a sum of independent {0, 1} random variables, then X is tightly concentrated around its expected value [X]. The fact that the random variables were {0, 1}-valued was not essential; similar concentration results hold if we simply assume that they are in some bounded range [−L, L]. One can also relax the independence assumption, as we will see next. Cons...
متن کاملLecture Notes on Stochastic Calculus (Part II)
2 Ito-Doeblin’s formula(s) 7 2.1 First formulations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.2 Generalizations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.3 Continuous semi-martingales . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.4 Integration by parts formula . . . . . . . . . . . ...
متن کاملOn Refined Versions of the Azuma-Hoeffding Inequality with Applications in Information Theory
This chapter introduces some concentration inequalities for discrete-time martingales with bounded increments, and it exemplifies some of their potential applications in information theory and related topics. The first part of this chapter introduces briefly discrete-time martingales and the Azuma-Hoeffding & McDiardmid’s inequalities which are widely used in this context. It then derives these...
متن کاملPAC-Bayesian Analysis of Martingales and Multiarmed Bandits
We present two alternative ways to apply PAC-Bayesian analysis to sequences of dependent random variables. The first is based on a new lemma that enables to bound expectations of convex functions of certain dependent random variables by expectations of the same functions of independent Bernoulli random variables. This lemma provides an alternative tool to Hoeffding-Azuma inequality to bound con...
متن کامل