Concentration inequalities for order statistics Using the entropy method and Rényi s representation



Similar documents
STAT 830 Convergence in Distribution

Tail inequalities for order statistics of log-concave vectors and applications

Lecture 13: Martingales

ON LIMIT LAWS FOR CENTRAL ORDER STATISTICS UNDER POWER NORMALIZATION. E. I. Pancheva, A. Gacovska-Barandovska

The Expectation Maximization Algorithm A short tutorial

Introduction to Probability

Aggregate Loss Models

Lecture 8: Signal Detection and Noise Assumption

How To Prove The Dirichlet Unit Theorem

Random graphs with a given degree sequence

Order statistics and concentration of l r norms for log-concave vectors

Gambling and Data Compression

NOV /II. 1. Let f(z) = sin z, z C. Then f(z) : 3. Let the sequence {a n } be given. (A) is bounded in the complex plane

Master s Theory Exam Spring 2006

Adaptive Online Gradient Descent

. (3.3) n Note that supremum (3.2) must occur at one of the observed values x i or to the left of x i.

Taylor and Maclaurin Series

Exponential Distribution

Probability Generating Functions

n k=1 k=0 1/k! = e. Example 6.4. The series 1/k 2 converges in R. Indeed, if s n = n then k=1 1/k, then s 2n s n = 1 n

CHAPTER II THE LIMIT OF A SEQUENCE OF NUMBERS DEFINITION OF THE NUMBER e.

What is Statistics? Lecture 1. Introduction and probability review. Idea of parametric inference

Lecture 13 Linear quadratic Lyapunov theory

Linear Threshold Units

Random variables P(X = 3) = P(X = 3) = 1 8, P(X = 1) = P(X = 1) = 3 8.

Marshall-Olkin distributions and portfolio credit risk

MATH4427 Notebook 2 Spring MATH4427 Notebook Definitions and Examples Performance Measures for Estimators...

THE CENTRAL LIMIT THEOREM TORONTO

Week 1: Introduction to Online Learning

3. Convex functions. basic properties and examples. operations that preserve convexity. the conjugate function. quasiconvex functions

2DI36 Statistics. 2DI36 Part II (Chapter 7 of MR)

The mean field traveling salesman and related problems

Notes on Factoring. MA 206 Kurt Bryan

Mathematical Finance

Lecture Notes 1. Brief Review of Basic Probability

Modern Optimization Methods for Big Data Problems MATH11146 The University of Edinburgh

MATHEMATICAL METHODS OF STATISTICS

Universal Algorithm for Trading in Stock Market Based on the Method of Calibration

M/M/1 and M/M/m Queueing Systems

Elementary factoring algorithms

Annuities. Lecture: Weeks Lecture: Weeks 9-11 (STT 455) Annuities Fall Valdez 1 / 43

2.3 Convex Constrained Optimization Problems

The Exponential Distribution

A Uniform Asymptotic Estimate for Discounted Aggregate Claims with Subexponential Tails

LECTURE 4. Last time: Lecture outline

Permanents, Order Statistics, Outliers, and Robustness

An example of a computable

Notes for a graduate-level course in asymptotics for statisticians. David R. Hunter Penn State University

e.g. arrival of a customer to a service station or breakdown of a component in some system.

From Binomial Trees to the Black-Scholes Option Pricing Formulas

Mathematics for Econometrics, Fourth Edition

IEOR 6711: Stochastic Models, I Fall 2012, Professor Whitt, Final Exam SOLUTIONS

The Variability of P-Values. Summary

1 Norms and Vector Spaces

Lectures 5-6: Taylor Series

A FIRST COURSE IN OPTIMIZATION THEORY

Factorization Methods: Very Quick Overview

Message-passing sequential detection of multiple change points in networks

Extracting correlation structure from large random matrices

Quadratic forms Cochran s theorem, degrees of freedom, and all that

A SURVEY ON CONTINUOUS ELLIPTICAL VECTOR DISTRIBUTIONS

UNIFORM ASYMPTOTICS FOR DISCOUNTED AGGREGATE CLAIMS IN DEPENDENT RISK MODELS

The Discrete Binomial Model for Option Pricing

A PRIORI ESTIMATES FOR SEMISTABLE SOLUTIONS OF SEMILINEAR ELLIPTIC EQUATIONS. In memory of Rou-Huai Wang

A generalized allocation scheme

LOGNORMAL MODEL FOR STOCK PRICES

MATH10212 Linear Algebra. Systems of Linear Equations. Definition. An n-dimensional vector is a row or a column of n numbers (or letters): a 1.

The sample space for a pair of die rolls is the set. The sample space for a random number between 0 and 1 is the interval [0, 1].

Extremal equilibria for reaction diffusion equations in bounded domains and applications.

Mathematics Course 111: Algebra I Part IV: Vector Spaces

Lectures on Stochastic Processes. William G. Faris

Lecture 13: Factoring Integers

Discussion on the paper Hypotheses testing by convex optimization by A. Goldenschluger, A. Juditsky and A. Nemirovski.

How to Gamble If You Must

Lecture 4: BK inequality 27th August and 6th September, 2007

THE DYING FIBONACCI TREE. 1. Introduction. Consider a tree with two types of nodes, say A and B, and the following properties:

Nonparametric adaptive age replacement with a one-cycle criterion

Introduction to Detection Theory

U.C. Berkeley CS276: Cryptography Handout 0.1 Luca Trevisan January, Notes on Algebra

The Black-Scholes-Merton Approach to Pricing Options

EC3070 FINANCIAL DERIVATIVES

The Basics of Graphical Models

Lecture 6: Discrete & Continuous Probability and Random Variables

ALGORITHMIC TRADING WITH MARKOV CHAINS

6. Define log(z) so that π < I log(z) π. Discuss the identities e log(z) = z and log(e w ) = w.

Ideal Class Group and Units

Insurance. Michael Peters. December 27, 2013

Corrected Diffusion Approximations for the Maximum of Heavy-Tailed Random Walk

SF2940: Probability theory Lecture 8: Multivariate Normal Distribution

Monte Carlo Simulation

Economics 1011a: Intermediate Microeconomics

THE FUNDAMENTAL THEOREM OF ALGEBRA VIA PROPER MAPS

OPTIMAL SELECTION BASED ON RELATIVE RANK* (the "Secretary Problem")

Chapter 7. BANDIT PROBLEMS.

Transcription:

Concentration inequalities for order statistics Using the entropy method and Rényi s representation Maud Thomas 1 in collaboration with Stéphane Boucheron 1 1 LPMA Université Paris-Diderot High Dimensional Probability VII Cargèse, May 26-30, 2014 1 / 19

Background: order statistics Sample: X 1,..., X n i.i.d. F. Order statistics X p1q ě... ě X pnq non-increasing rearrangement of X 1,..., X n. Goal X p1q : sample maximum. X pn{2q : sample median. @k, PtX pkq ď tu ř n `n i k i F i ptqp1 F ptqq n i. Classical statistic theory and Extreme Value Theory provide: Asymptotic distributions. Convergence of moments. derive simple, non-asymptotic variance/tail bounds for order statistics. 2 / 19

Background: concentration Concentration of measure phenomenon Any function of many independent random variables that does not depend too much on any of them is concentrated around its mean value. Example: Gaussian concentration X a standard Gaussian vector and Z f px q. Poincaré s inequality: VarrZs ď E} f } 2. Gross logarithmic Sobolev inequality: EntrZ 2 s ď 2E} f } 2. Cirelson s inequality: PtZ ě EZ ` tu ď expp t 2 {p2l 2 qq if } f } ď L. 3 / 19

Gaussian case and the Poincaré s inequality f px 1,..., X n q X pkq the rank k order statistic of a sample is a simple function of n independent random variables. f 1. X i are standard Gaussian. Poincaré s inequality ñ VarrX pkq s ď 1. Extreme Value Theory ñ VarrX p1q s Op1{ log nq. Classical statistic theory ñ VarrX pn{2q s Op1{nq. We do not understand (clearly) in which way order statistics are a smooth function of the sample. 4 / 19

Order statistics and spacings Proposition (Boucheron, T. (2012)) For all 0 ă k ď n{2 VarrX pkq s ď ke `Xpkq X pk`1q 2ı ker 2 k s. For all λ P R, Ent e λx pkq : λerx pkq e λx pkq s Ere λx pkqs log Ere λx pkqs ď ke e λx pk`1q ψpλpxpkq X pk`1q qq ke e λx pk`1q ψpλ k q with ψpxq 1 ` px 1qe x. 5 / 19

Remarks V k : k 2 k is called the Efron-Stein estimate of the variance of X pkq. Without any assumption such as: F belongs to the max-domain of attraction of an extreme value distribution G, i.e lim F n pa nñ`8 nx ` b nq Gpxq for every continuity point x of G. px pkq q is a sequence of extreme order statistics, if k fixed, n Ñ 8; central order statistics, if k{n Ñ p P p0, 1q while, n Ñ 8; intermediate order statistics, if k{n Ñ 0, k Ñ 8. 6 / 19

Proof Efron-Stein inequality (Efron, Stein (1981)) Let f : R n Ñ R be measurable, and let Z f px 1,..., X n q. Let Z i f i px 1,..., X i 1, X i`1,..., X n q where f i : R n 1 Ñ R is an arbitrary measurable function. Suppose Z is square-integrable, then: «ff nÿ VarrZs ď E pz Z i q 2. i 1 Modified logarithmic Sobolev inequality (Wu(2000); Massart (2000)) Let τpxq e x x 1. With the same notations, for any λ P R, Ent e «ff ÿ n λz ď E e λz τ p λpz Z i qq. i 1 7 / 19

Graphical assessment 1 2 3 4 5 + + + + + + + + + + Ratio between the Efron-Stein estimate and the variance of the maximum of n independent Gaussian random variables. n 2 p for p 1,..., 10. The asymptote is the line y 12{π 2 «1.22. 2 5 10 20 50 100 200 500 1000 8 / 19

Rényi s representation The order statistics of an exponential sample are distributed as partial sums of independent exponentially distributed random variables. Rényi s representation (Rényi (1953)) Let Y p1q ě Y p2q ě... ě Y pnq be the order statistics of an independent sample of the standard exponential distribution, then `Ypnq,..., Y piq,..., Y p1q ` En n,..., nÿ k i E k k,..., nÿ k 1 E k k where E 1,..., E n are i.i.d standard exponential random variables. 9 / 19

Quantile transformation Definition (Quantile function) F Ð ppq inf tx : F pxq ě pu, p P p0, 1q. Notation Uptq F Ð p1 1{tq, t P p1, 8q. Representation for order statistics If Y p1q ě... ě Y pnq are the order statistics of an exponential sample, then pu expqpy p1q q ě... ě pu expqpy pnq q are distributed as the order statistics of a sample drawn according to F. 10 / 19

Hazard rate, spacings and order statistics Definition (Hazard rate) The hazard rate h of a differentiable distribution function F is defined as: h F 1 {F F 1 {p1 F q. Lemma The distribution function F has non-decreasing hazard rate h, iff U exp is concave. Indeed, pu expq 1 1 h pu expq. If the distribution is log-concave, then the associated hazard rate is non-decreasing. 11 / 19

Variance bound for order statistics when the hazard rate is non-decreasing Recall: V k k 2 k. Proposition (Boucheron, T. (2012)) If F has non-decreasing hazard rate h, then for 1 ď k ď n{2, Var X pkq ď EVk ď 2 k E 1 hpx pk`1q q 2j. 12 / 19

Towards an exponential Efron-Stein inequality Definition (Exponential Efron-Stein inequality) Let Z f px 1,..., X n q where X 1,..., X n are independent random variables and V its Efron-Stein estimate of the variance of Z. Z satisfies an exponential Efron-Stein inequality if for all θ, λ ą 0 such that λθ ă 1 and E e λv {θ ă 8: Problem ı log E e λpz EZq ď λθ ı 1 λθ log E e λv {θ For an exponential sample, E e λv {θ 8. ë Find another decoupling inequality. ë Negative Association.. 13 / 19

Decoupling inequality: negative association Negative association X and Y are negatively associated if for any non-decreasing functions f, g E rf px qgpy qs ď E rf px qs E rgpy qs. Lemma If the distribution function F has non-decreasing hazard rate, then X pk`1q and k X pkq X pk`1q are negatively associated. 14 / 19

Exponential Efron-Stein inequality for order statistics Proposition (Boucheron, T. (2012)) If F has non-decreasing hazard rate h, then for λ ě 0, and 1 ď k ď n{2, log Ee λpx pkq EX pkq q ď λ k 2 E k `eλ k 1 λ k 2 E «c Vk k ff e λ? V k {k 1. 15 / 19

Gaussian hazard rate Uptq Φ Ð p1 1{tq for t ą 1. 4 4 3 3 U(exp(x)) 2 1 U(2 exp(x)) 2 0 Gaussian distribution 1 Absolute value of Gaussian random variable 1 0 0 2 4 6 8 10 0 2 4 6 8 10 16 / 19

Variance of absolute values of Gaussian random variables Proposition (Boucheron, T. (2012)) Let n ě 3, let X pkq be the rank k order statistic of absolute values of n standard independent Gaussian random variables, VarrX pkq s ď 1 k log 2 log ` 2n k 8 logp1 ` 4 k log log ` 2n k q. For the maximum (k 1), the bound becomes: 1 8 log 2 log 2n logp1 ` 4 log log 2nq. M n : maximum of n standard Gaussian r.v Chatterjee (Talagrand L1-L2 inequality): VarrM ns ď 1 1`log n. Nourdin (Ornstein-Uhlenbeck process): VarrM ns ď 2 log n. 17 / 19

Bernstein inequality for the maximum of absolute values of Gaussian random variables Theorem (Boucheron, T. (2012)) For n such that the solution v n of equation is smaller than 1, for all 0 ď λ ă 1? vn, 16{x ` logp1 ` 2{x ` 4 logp4{xqq logp2nq log Ee λpx p1q EX p1q q ď v n λ 2 2p1?v n λq. 18 / 19

Thank you for your attention! 19 / 19