Sharp Finite-Time Iterated-Logarithm Martingale Concentration

05/12/2014
by   Akshay Balsubramani, et al.
0

We give concentration bounds for martingales that are uniform over finite times and extend classical Hoeffding and Bernstein inequalities. We also demonstrate our concentration bounds to be optimal with a matching anti-concentration inequality, proved using the same method. Together these constitute a finite-time version of the law of the iterated logarithm, and shed light on the relationship between it and the central limit theorem.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/30/2020

Sharp finite-sample large deviation bounds for independent variables

We show an extension of Sanov's theorem in large deviations theory, cont...
research
12/17/2017

A Survey of Concentration Inequalities for U-Statistics

The aim of this paper is to discuss various concentration inequali- ties...
research
06/25/2023

Dual Induction CLT for High-dimensional m-dependent Data

In this work, we provide a 1/√(n)-rate finite sample Berry-Esseen bound ...
research
05/09/2018

Concentration inequalities for randomly permuted sums

Initially motivated by the study of the non-asymptotic properties of non...
research
12/18/2020

Local Dvoretzky-Kiefer-Wolfowitz confidence bands

In this paper, we revisit the concentration inequalities for the supremu...
research
12/08/2020

A Concentration Inequality for the Facility Location Problem

We give a concentration inequality for a stochastic version of the facil...
research
10/12/2021

Uniform concentration bounds for frequencies of rare events

New Vapnik and Chervonkis type concentration inequalities are derived fo...

Please sign up or login with your details

Forgot password? Click here to reset