Tail inequalities for additive functionals and empirical processes of. Markov chains

Size: px
Start display at page:

Download "Tail inequalities for additive functionals and empirical processes of. Markov chains"

Transcription

1 Tail inequalities for additive functionals and empirical processes of geometrically ergodic Markov chains University of Warsaw Banff, June 2009

2 Geometric ergodicity Definition A Markov chain X = (X n ) n 1 on a Polish space X with a transition function P(, ): X B(X ) [0, 1] and a unique stationary distribution π is called geometrically ergodic if there exists ρ < 1 such that for every x X there exists a constant M(x), such that P n (x, ) π TV M(x)ρ n. If M(x) can be taken independent of x, then X is called uniformly ergodic.

3 Main question What is the tail decay of S := n f (X i ), i=1 where f : X R, E π f = 0, f a

4 Main question What is the tail decay of S := n f (X i ), i=1 where f : X R, E π f = 0, f a or S := sup f F n f (X i ), i=1 where F - a countable class of f s as above.

5 Regeneration method, split chain Definition A set C B(X ) is called a small set if there exists a probability measure ν on X and ε > 0 such that for all x C and A B(X ) and for all x X. P(x, A) εν(a) P x ( n>1 X n C) = 1

6 Regeneration method, split chain We can define a new chain ( X n, R n ) in the following way. Given X n = x, if x / C, draw X n+1 from P(x, ), set R n = 0

7 Regeneration method, split chain We can define a new chain ( X n, R n ) in the following way. Given X n = x, if x / C, draw X n+1 from P(x, ), set R n = 0 if x C, toss a coin with probability of heads equal to ε

8 Regeneration method, split chain We can define a new chain ( X n, R n ) in the following way. Given X n = x, if x / C, draw X n+1 from P(x, ), set R n = 0 if x C, toss a coin with probability of heads equal to ε heads: draw X n+1 from ν, set R n = 1

9 Regeneration method, split chain We can define a new chain ( X n, R n ) in the following way. Given X n = x, if x / C, draw X n+1 from P(x, ), set R n = 0 if x C, toss a coin with probability of heads equal to ε heads: draw X n+1 from ν, set R n = 1 tails: draw X n+1 from and set R n = 0. P(x, ) εν( ). 1 ε

10 Regeneration method, split chain We can define a new chain ( X n, R n ) in the following way. Given X n = x, if x / C, draw X n+1 from P(x, ), set R n = 0 if x C, toss a coin with probability of heads equal to ε heads: draw X n+1 from ν, set R n = 1 tails: draw X n+1 from P(x, ) εν( ). 1 ε Since and set R n = 0. P(x, ) εν( ) εν( ) + (1 ε) = P(x, ), 1 ε X n is again a Markov chain with transition function P (and we will identify it with X n ).

11 Regeneration method, split chain Let T 1 = inf{n > 0: R n = 1}, T i+1 = inf{n > 0: R T T i +n = 1} and Y 0 = (X 1,..., X T1 ) Y i = (X T T i +1,..., X T T i+1 ). Fact Blocks Y i, i 0 are independent, blocks Y i, i 1 are i.i.d If f : X R and Z i = Z i (f ) = T T i+1 j=t T i +1 then for i 1, EZ i = (ET 2 ) 1 E π f. f (X j ),

12 Regeneration method, summary We can write f (X 1 ) f (X n ) = Z Z N + where N = sup{i N: T T i+1 n}, Z i = Z i (f ) = Z 0 = Z 0 (f ) = T 1 n i=1 T T i+1 i=t T i +1 f (X i ), n i=t T N+1 +1 f (X i ), i 1, and use the i.i.d. theory to analyze additive functionals. f (X i ),

13 Regeneration method, summary The idea goes back to Nummelin (early 80 s), developed subsequently by Meyn and Tweedie for proving limit theorems. A sample recent result is Theorem (Bednorz, Latała, Łatuszyński) If E π f 2 <, E π f = 0 then f (X 1 ) f (X n ) n converges weakly iff EZ 1 (f ) 2 <. The limiting distribution is N (0, σ 2 ), where σ 2 = Var(Z 1 )/(ET 2 ). For concentration inequalities, the regeneration method has been used e.g. by Clémençon (2001) and Douc, Guillin, Moulines (2008).

14 Drift conditions Theorem (Meyn, Tweedie) A Markov chain X n is geometrically ergodic iff there exists V : X [1, ) and constants λ < 1 and K <, such that PV (x) = X V (y)p(x, dy) Theorem (Meyn & Tweedie, Baxendale) { λv (x) for x / C, K for x C If X 1 µ, E µ V < then T 1 ψ1, T 2 ψ1 <. Corollary Consider a set F of functions f : X R, such that for all f F, f a. Then sup Z i (f ) ψ1 Caτ, f F where τ = max( T 1 ψ1, T 2 ψ1 ).

15 Main theorem a single function Theorem (R.A. 2008) Consider a function f : X R, such that f a and E π f = 0. Define also the random variable Then for all t > 0, S = n f (X i ). i=1 ( ) ( P S > t K exp 1 ( K min t 2 t )) n(et 2 ) 1, VarZ 1 τ 2. a log n Remark: (ET 2 ) 1 VarZ 1 is the variance of the limiting normal variable.

16 Main theorem empirical processes Theorem (R.A. 2008) Consider a countable class F of measurable functions f : X R, such that f a and E π f = 0. Define the random variable S = sup f F n f (X i ) i=1 and the asymptotic weak variance Then for all t 1, σ 2 = sup VarZ 1 (f )/ET 2. f F ( ) ( P S K ES + t K exp 1 ( t 2 K min nσ 2, t )) τ 3 (ET 2 ) 1. a log n

17 Sketch of the proof Recall that f (X 1 ) f (X n ) = Z 0 + Z Z N + n f (X i ), i=t T N+1 +1

18 Sketch of the proof Recall that f (X 1 ) f (X n ) = Z 0 + Z Z N + n f (X i ), i=t T N+1 +1 Z 0 ψ1 Caτ = P( Z 0 t) 2e ct/(aτ).

19 Sketch of the proof Recall that f (X 1 ) f (X n ) = Z 0 + Z Z N + n f (X i ), i=t T N+1 +1 Z 0 ψ1 Caτ = P( Z 0 t) 2e ct/(aτ). One can easily show that (n (T T N+1 )) + ψ1 Cτ log τ This allows to handle the last term.

20 Sketch of the proof Recall that f (X 1 ) f (X n ) = Z 0 + Z Z N + n f (X i ), i=t T N+1 +1 Z 0 ψ1 Caτ = P( Z 0 t) 2e ct/(aτ). One can easily show that (n (T T N+1 )) + ψ1 Cτ log τ This allows to handle the last term. What remains is Z Z N - a sum of random length.

21 By the LLN, N n/(et 2 ) (quantitative bounds by Bernstein s ψ 1 inequality), so with high probability Z Z N max i Cn/(ET 2 ) Z Z i and we can use Levy-type inequality due to Montgomery-Smith.

22 By the LLN, N n/(et 2 ) (quantitative bounds by Bernstein s ψ 1 inequality), so with high probability Z Z N max i Cn/(ET 2 ) Z Z i and we can use Levy-type inequality due to Montgomery-Smith. We are left with Z 1 (f ) Z Cn/(ET2 )(f ) where Z i are i.i.d. and we control VarZ i (f ) and sup f F Z i (f ) ψ1.

23 Inequality for independent variables Consider now X 1,..., X n independent r.v. s F a countable class of measurable functions f, s.t. Ef (X i ) = 0 and for some α (0, 1], sup f (X i ) ψα <. f S = sup f F σ 2 = sup f F n f (X i ). i=1 n Ef (X i ) 2. i=1

24 Inequality for independent variables Theorem (R.A. 2008) Under the above assumptions, for all 0 < η < 1 and δ > 0, t 0, P(S (1 + η)es + t), P(S (1 η)es t) ( t 2 ) exp 2(1 + δ)σ 2 ( ( t ) α ) + 3 exp C max i sup f F f (X i ) ψα where C = C(α, η, δ).

25 Back to Markov chains Since max i k Y i ψ1 C max i k Y i ψ1 log k, we can apply the result for independent variables to Z 1 (f ) Z Cn/(ET2 )(f ).

26 Back to Markov chains Since max i k Y i ψ1 C max i k Y i ψ1 log k, we can apply the result for independent variables to Z 1 (f ) Z Cn/(ET2 )(f ). In the empirical processes setting one also has to bound in terms of E sup Z 1 (f ) Z Cn/(ET2 )(f ) f F E sup f (X 1 ) f (X n ) f F (optional sampling + concentration for N)

27 How to handle the independent case? truncate and re-center the variables

28 How to handle the independent case? truncate and re-center the variables use Talagrand s inequality for the bounded part

29 How to handle the independent case? truncate and re-center the variables use Talagrand s inequality for the bounded part use another Talagrand s inequality to handle the unbounded part: Theorem (Talagrand) For independent, centered Banach space valued variables Z i and α (0, 1], Z Z n ψα C α ( Z Z n 1 + max i n Z i ψα ). In our case the Banach space is l (F)

30 How to handle the independent case? truncate and re-center the variables use Talagrand s inequality for the bounded part use another Talagrand s inequality to handle the unbounded part: Theorem (Talagrand) For independent, centered Banach space valued variables Z i and α (0, 1], Z Z n ψα C α ( Z Z n 1 + max i n Z i ψα ). In our case the Banach space is l (F) Truncation at the level of E max i sup f f (X i ) makes the unbounded part satisfy Z Z n 1 CE max i n Z i C α max i n Z i ψα. (Hoffman-Jørgensen inequality).

31 Optimality In the ineq. for independent variables (α = 1), log n in the exponent is optimal: P(X i = ±r) = 1 2 e r, P(X i = 0) = 1 e r, r. This example can be emulated with Markov chains which gives optimality of log n.

32 Final comments The same scheme can be applied under the assumption that T i ψα < (α 1). Unbounded functions: if f ψα(π) < then Z i ψα/2 <, which together with some additional arguments gives inequalities for the chain started from ν (W. Bednorz, R.A., unpublished), Using regeneration one can also obtain a bounded difference type inequality for symmetric functions (recovering e.g. Hoeffding inequalities for U-statistics in the Markov setting).

33 Some open (???) questions Can one get estimates of the form ( P(S (1+η)ES+t) exp t 2 ) (2 + δ)(et 2 ) 1 VarZ 1 What about drift conditions on f, guaranteeing that Z i (f ) ψ1 <? Important for applications to MCMC algorithms partial results by W. Bednorz (unpublished) Is there a nice characterizations of Orlicz functions for which a Hoffman-Joergensen type inequality holds? M. Talagrand > characterization for functions of the form ψ(x) = exp(xξ(x)) (where x large enough, ξ nondecreasing): ξ(e u ) Lξ(u) for u large enough. +K (η, δ)...?

34 Thank you

Practical conditions on Markov chains for weak convergence of tail empirical processes

Practical conditions on Markov chains for weak convergence of tail empirical processes Practical conditions on Markov chains for weak convergence of tail empirical processes Olivier Wintenberger University of Copenhagen and Paris VI Joint work with Rafa l Kulik and Philippe Soulier Toronto,

More information

A regeneration proof of the central limit theorem for uniformly ergodic Markov chains

A regeneration proof of the central limit theorem for uniformly ergodic Markov chains A regeneration proof of the central limit theorem for uniformly ergodic Markov chains By AJAY JASRA Department of Mathematics, Imperial College London, SW7 2AZ, London, UK and CHAO YANG Department of Mathematics,

More information

Limit theorems for dependent regularly varying functions of Markov chains

Limit theorems for dependent regularly varying functions of Markov chains Limit theorems for functions of with extremal linear behavior Limit theorems for dependent regularly varying functions of In collaboration with T. Mikosch Olivier Wintenberger wintenberger@ceremade.dauphine.fr

More information

STA205 Probability: Week 8 R. Wolpert

STA205 Probability: Week 8 R. Wolpert INFINITE COIN-TOSS AND THE LAWS OF LARGE NUMBERS The traditional interpretation of the probability of an event E is its asymptotic frequency: the limit as n of the fraction of n repeated, similar, and

More information

A tail inequality for suprema of unbounded empirical processes with applications to Markov chains

A tail inequality for suprema of unbounded empirical processes with applications to Markov chains E l e c t r o n i c J o u r n a l o P r o b a b i l i t y Vol. 13 2008, Paper no. 34, pages 1000 1034. Journal URL http://www.math.washington.edu/~ejpecp/ A tail inequality or suprema o unbounded empirical

More information

When is a Markov chain regenerative?

When is a Markov chain regenerative? When is a Markov chain regenerative? Krishna B. Athreya and Vivekananda Roy Iowa tate University Ames, Iowa, 50011, UA Abstract A sequence of random variables {X n } n 0 is called regenerative if it can

More information

arxiv:math/ v2 [math.pr] 16 Mar 2007

arxiv:math/ v2 [math.pr] 16 Mar 2007 CHARACTERIZATION OF LIL BEHAVIOR IN BANACH SPACE UWE EINMAHL a, and DELI LI b, a Departement Wiskunde, Vrije Universiteit Brussel, arxiv:math/0608687v2 [math.pr] 16 Mar 2007 Pleinlaan 2, B-1050 Brussel,

More information

Lectures on Stochastic Stability. Sergey FOSS. Heriot-Watt University. Lecture 4. Coupling and Harris Processes

Lectures on Stochastic Stability. Sergey FOSS. Heriot-Watt University. Lecture 4. Coupling and Harris Processes Lectures on Stochastic Stability Sergey FOSS Heriot-Watt University Lecture 4 Coupling and Harris Processes 1 A simple example Consider a Markov chain X n in a countable state space S with transition probabilities

More information

STA 711: Probability & Measure Theory Robert L. Wolpert

STA 711: Probability & Measure Theory Robert L. Wolpert STA 711: Probability & Measure Theory Robert L. Wolpert 6 Independence 6.1 Independent Events A collection of events {A i } F in a probability space (Ω,F,P) is called independent if P[ i I A i ] = P[A

More information

arxiv: v1 [math.pr] 19 Sep 2007

arxiv: v1 [math.pr] 19 Sep 2007 arxiv:0709.3110v1 [math.pr] 19 Sep 2007 A tail inequality or suprema o unbounded empirical processes with applications to Markov chains Rados law Adamczak June 11, 2008 Abstract We present an easy extension

More information

Simultaneous drift conditions for Adaptive Markov Chain Monte Carlo algorithms

Simultaneous drift conditions for Adaptive Markov Chain Monte Carlo algorithms Simultaneous drift conditions for Adaptive Markov Chain Monte Carlo algorithms Yan Bai Feb 2009; Revised Nov 2009 Abstract In the paper, we mainly study ergodicity of adaptive MCMC algorithms. Assume that

More information

New Bernstein and Hoeffding type inequalities for regenerative Markov chains

New Bernstein and Hoeffding type inequalities for regenerative Markov chains New Bernstein and Hoeffding type inequalities for regenerative Markov chains Patrice Bertail Gabriela Ciolek To cite this version: Patrice Bertail Gabriela Ciolek. New Bernstein and Hoeffding type inequalities

More information

STAT 200C: High-dimensional Statistics

STAT 200C: High-dimensional Statistics STAT 200C: High-dimensional Statistics Arash A. Amini May 30, 2018 1 / 59 Classical case: n d. Asymptotic assumption: d is fixed and n. Basic tools: LLN and CLT. High-dimensional setting: n d, e.g. n/d

More information

Ergodic Theorems. Samy Tindel. Purdue University. Probability Theory 2 - MA 539. Taken from Probability: Theory and examples by R.

Ergodic Theorems. Samy Tindel. Purdue University. Probability Theory 2 - MA 539. Taken from Probability: Theory and examples by R. Ergodic Theorems Samy Tindel Purdue University Probability Theory 2 - MA 539 Taken from Probability: Theory and examples by R. Durrett Samy T. Ergodic theorems Probability Theory 1 / 92 Outline 1 Definitions

More information

Strong approximation for additive functionals of geometrically ergodic Markov chains

Strong approximation for additive functionals of geometrically ergodic Markov chains Strong approximation for additive functionals of geometrically ergodic Markov chains Florence Merlevède Joint work with E. Rio Université Paris-Est-Marne-La-Vallée (UPEM) Cincinnati Symposium on Probability

More information

Weak and strong moments of l r -norms of log-concave vectors

Weak and strong moments of l r -norms of log-concave vectors Weak and strong moments of l r -norms of log-concave vectors Rafał Latała based on the joint work with Marta Strzelecka) University of Warsaw Minneapolis, April 14 2015 Log-concave measures/vectors A measure

More information

Some Results on the Ergodicity of Adaptive MCMC Algorithms

Some Results on the Ergodicity of Adaptive MCMC Algorithms Some Results on the Ergodicity of Adaptive MCMC Algorithms Omar Khalil Supervisor: Jeffrey Rosenthal September 2, 2011 1 Contents 1 Andrieu-Moulines 4 2 Roberts-Rosenthal 7 3 Atchadé and Fort 8 4 Relationship

More information

Ergodicity in data assimilation methods

Ergodicity in data assimilation methods Ergodicity in data assimilation methods David Kelly Andy Majda Xin Tong Courant Institute New York University New York NY www.dtbkelly.com April 15, 2016 ETH Zurich David Kelly (CIMS) Data assimilation

More information

On Reparametrization and the Gibbs Sampler

On Reparametrization and the Gibbs Sampler On Reparametrization and the Gibbs Sampler Jorge Carlos Román Department of Mathematics Vanderbilt University James P. Hobert Department of Statistics University of Florida March 2014 Brett Presnell Department

More information

Generalization theory

Generalization theory Generalization theory Daniel Hsu Columbia TRIPODS Bootcamp 1 Motivation 2 Support vector machines X = R d, Y = { 1, +1}. Return solution ŵ R d to following optimization problem: λ min w R d 2 w 2 2 + 1

More information

1 Sequences of events and their limits

1 Sequences of events and their limits O.H. Probability II (MATH 2647 M15 1 Sequences of events and their limits 1.1 Monotone sequences of events Sequences of events arise naturally when a probabilistic experiment is repeated many times. For

More information

Phenomena in high dimensions in geometric analysis, random matrices, and computational geometry Roscoff, France, June 25-29, 2012

Phenomena in high dimensions in geometric analysis, random matrices, and computational geometry Roscoff, France, June 25-29, 2012 Phenomena in high dimensions in geometric analysis, random matrices, and computational geometry Roscoff, France, June 25-29, 202 BOUNDS AND ASYMPTOTICS FOR FISHER INFORMATION IN THE CENTRAL LIMIT THEOREM

More information

Subgaussian concentration inequalities for geometrically ergodic Markov chains

Subgaussian concentration inequalities for geometrically ergodic Markov chains Subgaussian concentration inequalities for geometrically ergodic Markov chains Jérôme Dedecker, Sébastien Gouëzel To cite this version: Jérôme Dedecker, Sébastien Gouëzel. Subgaussian concentration inequalities

More information

18.175: Lecture 8 Weak laws and moment-generating/characteristic functions

18.175: Lecture 8 Weak laws and moment-generating/characteristic functions 18.175: Lecture 8 Weak laws and moment-generating/characteristic functions Scott Sheffield MIT 18.175 Lecture 8 1 Outline Moment generating functions Weak law of large numbers: Markov/Chebyshev approach

More information

Notes 15 : UI Martingales

Notes 15 : UI Martingales Notes 15 : UI Martingales Math 733 - Fall 2013 Lecturer: Sebastien Roch References: [Wil91, Chapter 13, 14], [Dur10, Section 5.5, 5.6, 5.7]. 1 Uniform Integrability We give a characterization of L 1 convergence.

More information

Concentration inequalities and the entropy method

Concentration inequalities and the entropy method Concentration inequalities and the entropy method Gábor Lugosi ICREA and Pompeu Fabra University Barcelona what is concentration? We are interested in bounding random fluctuations of functions of many

More information

Consistency of the maximum likelihood estimator for general hidden Markov models

Consistency of the maximum likelihood estimator for general hidden Markov models Consistency of the maximum likelihood estimator for general hidden Markov models Jimmy Olsson Centre for Mathematical Sciences Lund University Nordstat 2012 Umeå, Sweden Collaborators Hidden Markov models

More information

Problem Sheet 1. You may assume that both F and F are σ-fields. (a) Show that F F is not a σ-field. (b) Let X : Ω R be defined by 1 if n = 1

Problem Sheet 1. You may assume that both F and F are σ-fields. (a) Show that F F is not a σ-field. (b) Let X : Ω R be defined by 1 if n = 1 Problem Sheet 1 1. Let Ω = {1, 2, 3}. Let F = {, {1}, {2, 3}, {1, 2, 3}}, F = {, {2}, {1, 3}, {1, 2, 3}}. You may assume that both F and F are σ-fields. (a) Show that F F is not a σ-field. (b) Let X :

More information

Heavy Tailed Time Series with Extremal Independence

Heavy Tailed Time Series with Extremal Independence Heavy Tailed Time Series with Extremal Independence Rafa l Kulik and Philippe Soulier Conference in honour of Prof. Herold Dehling Bochum January 16, 2015 Rafa l Kulik and Philippe Soulier Regular variation

More information

Selected Exercises on Expectations and Some Probability Inequalities

Selected Exercises on Expectations and Some Probability Inequalities Selected Exercises on Expectations and Some Probability Inequalities # If E(X 2 ) = and E X a > 0, then P( X λa) ( λ) 2 a 2 for 0 < λ

More information

High Dimensional Probability

High Dimensional Probability High Dimensional Probability for Mathematicians and Data Scientists Roman Vershynin 1 1 University of Michigan. Webpage: www.umich.edu/~romanv ii Preface Who is this book for? This is a textbook in probability

More information

The coupling method - Simons Counting Complexity Bootcamp, 2016

The coupling method - Simons Counting Complexity Bootcamp, 2016 The coupling method - Simons Counting Complexity Bootcamp, 2016 Nayantara Bhatnagar (University of Delaware) Ivona Bezáková (Rochester Institute of Technology) January 26, 2016 Techniques for bounding

More information

SUPPLEMENT TO PAPER CONVERGENCE OF ADAPTIVE AND INTERACTING MARKOV CHAIN MONTE CARLO ALGORITHMS

SUPPLEMENT TO PAPER CONVERGENCE OF ADAPTIVE AND INTERACTING MARKOV CHAIN MONTE CARLO ALGORITHMS Submitted to the Annals of Statistics SUPPLEMENT TO PAPER CONERGENCE OF ADAPTIE AND INTERACTING MARKO CHAIN MONTE CARLO ALGORITHMS By G Fort,, E Moulines and P Priouret LTCI, CNRS - TELECOM ParisTech,

More information

Existence, Uniqueness and Stability of Invariant Distributions in Continuous-Time Stochastic Models

Existence, Uniqueness and Stability of Invariant Distributions in Continuous-Time Stochastic Models Existence, Uniqueness and Stability of Invariant Distributions in Continuous-Time Stochastic Models Christian Bayer and Klaus Wälde Weierstrass Institute for Applied Analysis and Stochastics and University

More information

Introduction to Machine Learning CMU-10701

Introduction to Machine Learning CMU-10701 Introduction to Machine Learning CMU-10701 Stochastic Convergence Barnabás Póczos Motivation 2 What have we seen so far? Several algorithms that seem to work fine on training datasets: Linear regression

More information

General Glivenko-Cantelli theorems

General Glivenko-Cantelli theorems The ISI s Journal for the Rapid Dissemination of Statistics Research (wileyonlinelibrary.com) DOI: 10.100X/sta.0000......................................................................................................

More information

Notes 1 : Measure-theoretic foundations I

Notes 1 : Measure-theoretic foundations I Notes 1 : Measure-theoretic foundations I Math 733-734: Theory of Probability Lecturer: Sebastien Roch References: [Wil91, Section 1.0-1.8, 2.1-2.3, 3.1-3.11], [Fel68, Sections 7.2, 8.1, 9.6], [Dur10,

More information

Faithful couplings of Markov chains: now equals forever

Faithful couplings of Markov chains: now equals forever Faithful couplings of Markov chains: now equals forever by Jeffrey S. Rosenthal* Department of Statistics, University of Toronto, Toronto, Ontario, Canada M5S 1A1 Phone: (416) 978-4594; Internet: jeff@utstat.toronto.edu

More information

Lecture 2 One too many inequalities

Lecture 2 One too many inequalities University of Illinois Department of Economics Spring 2017 Econ 574 Roger Koenker Lecture 2 One too many inequalities In lecture 1 we introduced some of the basic conceptual building materials of the course.

More information

Problem Points S C O R E Total: 120

Problem Points S C O R E Total: 120 PSTAT 160 A Final Exam Solution December 10, 2015 Name Student ID # Problem Points S C O R E 1 10 2 10 3 10 4 10 5 10 6 10 7 10 8 10 9 10 10 10 11 10 12 10 Total: 120 1. (10 points) Take a Markov chain

More information

ON CONVERGENCE RATES OF GIBBS SAMPLERS FOR UNIFORM DISTRIBUTIONS

ON CONVERGENCE RATES OF GIBBS SAMPLERS FOR UNIFORM DISTRIBUTIONS The Annals of Applied Probability 1998, Vol. 8, No. 4, 1291 1302 ON CONVERGENCE RATES OF GIBBS SAMPLERS FOR UNIFORM DISTRIBUTIONS By Gareth O. Roberts 1 and Jeffrey S. Rosenthal 2 University of Cambridge

More information

Theorem 2.1 (Caratheodory). A (countably additive) probability measure on a field has an extension. n=1

Theorem 2.1 (Caratheodory). A (countably additive) probability measure on a field has an extension. n=1 Chapter 2 Probability measures 1. Existence Theorem 2.1 (Caratheodory). A (countably additive) probability measure on a field has an extension to the generated σ-field Proof of Theorem 2.1. Let F 0 be

More information

On Differentiability of Average Cost in Parameterized Markov Chains

On Differentiability of Average Cost in Parameterized Markov Chains On Differentiability of Average Cost in Parameterized Markov Chains Vijay Konda John N. Tsitsiklis August 30, 2002 1 Overview The purpose of this appendix is to prove Theorem 4.6 in 5 and establish various

More information

Eleventh Problem Assignment

Eleventh Problem Assignment EECS April, 27 PROBLEM (2 points) The outcomes of successive flips of a particular coin are dependent and are found to be described fully by the conditional probabilities P(H n+ H n ) = P(T n+ T n ) =

More information

Lecture 4 Lebesgue spaces and inequalities

Lecture 4 Lebesgue spaces and inequalities Lecture 4: Lebesgue spaces and inequalities 1 of 10 Course: Theory of Probability I Term: Fall 2013 Instructor: Gordan Zitkovic Lecture 4 Lebesgue spaces and inequalities Lebesgue spaces We have seen how

More information

arxiv: v2 [math.st] 13 Sep 2016

arxiv: v2 [math.st] 13 Sep 2016 arxiv:1511.0175v [math.st] 13 Sep 016 Exponential inequalities for unbounded functions of geometrically ergodic Markov chains. Applications to quantitative error bounds for regenerative Metropolis algorithms.

More information

March 1, Florida State University. Concentration Inequalities: Martingale. Approach and Entropy Method. Lizhe Sun and Boning Yang.

March 1, Florida State University. Concentration Inequalities: Martingale. Approach and Entropy Method. Lizhe Sun and Boning Yang. Florida State University March 1, 2018 Framework 1. (Lizhe) Basic inequalities Chernoff bounding Review for STA 6448 2. (Lizhe) Discrete-time martingales inequalities via martingale approach 3. (Boning)

More information

CS281A/Stat241A Lecture 22

CS281A/Stat241A Lecture 22 CS281A/Stat241A Lecture 22 p. 1/4 CS281A/Stat241A Lecture 22 Monte Carlo Methods Peter Bartlett CS281A/Stat241A Lecture 22 p. 2/4 Key ideas of this lecture Sampling in Bayesian methods: Predictive distribution

More information

Lecture 1 Measure concentration

Lecture 1 Measure concentration CSE 29: Learning Theory Fall 2006 Lecture Measure concentration Lecturer: Sanjoy Dasgupta Scribe: Nakul Verma, Aaron Arvey, and Paul Ruvolo. Concentration of measure: examples We start with some examples

More information

The PAC Learning Framework -II

The PAC Learning Framework -II The PAC Learning Framework -II Prof. Dan A. Simovici UMB 1 / 1 Outline 1 Finite Hypothesis Space - The Inconsistent Case 2 Deterministic versus stochastic scenario 3 Bayes Error and Noise 2 / 1 Outline

More information

Convergence to equilibrium for rough differential equations

Convergence to equilibrium for rough differential equations Convergence to equilibrium for rough differential equations Samy Tindel Purdue University Barcelona GSE Summer Forum 2017 Joint work with Aurélien Deya (Nancy) and Fabien Panloup (Angers) Samy T. (Purdue)

More information

On the Bennett-Hoeffding inequality

On the Bennett-Hoeffding inequality On the Bennett-Hoeffding inequality of Iosif 1,2,3 1 Department of Mathematical Sciences Michigan Technological University 2 Supported by NSF grant DMS-0805946 3 Paper available at http://arxiv.org/abs/0902.4058

More information

Math 180B Homework 4 Solutions

Math 180B Homework 4 Solutions Math 80B Homework 4 Solutions Note: We will make repeated use of the following result. Lemma. Let (X n ) be a time-homogeneous Markov chain with countable state space S, let A S, and let T = inf { n 0

More information

Notes 18 : Optional Sampling Theorem

Notes 18 : Optional Sampling Theorem Notes 18 : Optional Sampling Theorem Math 733-734: Theory of Probability Lecturer: Sebastien Roch References: [Wil91, Chapter 14], [Dur10, Section 5.7]. Recall: DEF 18.1 (Uniform Integrability) A collection

More information

Chapter 7. Markov chain background. 7.1 Finite state space

Chapter 7. Markov chain background. 7.1 Finite state space Chapter 7 Markov chain background A stochastic process is a family of random variables {X t } indexed by a varaible t which we will think of as time. Time can be discrete or continuous. We will only consider

More information

Some functional (Hölderian) limit theorems and their applications (II)

Some functional (Hölderian) limit theorems and their applications (II) Some functional (Hölderian) limit theorems and their applications (II) Alfredas Račkauskas Vilnius University Outils Statistiques et Probabilistes pour la Finance Université de Rouen June 1 5, Rouen (Rouen

More information

Convergence to equilibrium of Markov processes (eventually piecewise deterministic)

Convergence to equilibrium of Markov processes (eventually piecewise deterministic) Convergence to equilibrium of Markov processes (eventually piecewise deterministic) A. Guillin Université Blaise Pascal and IUF Rennes joint works with D. Bakry, F. Barthe, F. Bolley, P. Cattiaux, R. Douc,

More information

Random Variables. Saravanan Vijayakumaran Department of Electrical Engineering Indian Institute of Technology Bombay

Random Variables. Saravanan Vijayakumaran Department of Electrical Engineering Indian Institute of Technology Bombay 1 / 13 Random Variables Saravanan Vijayakumaran sarva@ee.iitb.ac.in Department of Electrical Engineering Indian Institute of Technology Bombay August 8, 2013 2 / 13 Random Variable Definition A real-valued

More information

A primer on basic probability and Markov chains

A primer on basic probability and Markov chains A primer on basic probability and Markov chains David Aristo January 26, 2018 Contents 1 Basic probability 2 1.1 Informal ideas and random variables.................... 2 1.2 Probability spaces...............................

More information

Nonparametric regression with martingale increment errors

Nonparametric regression with martingale increment errors S. Gaïffas (LSTA - Paris 6) joint work with S. Delattre (LPMA - Paris 7) work in progress Motivations Some facts: Theoretical study of statistical algorithms requires stationary and ergodicity. Concentration

More information

Modern Discrete Probability Spectral Techniques

Modern Discrete Probability Spectral Techniques Modern Discrete Probability VI - Spectral Techniques Background Sébastien Roch UW Madison Mathematics December 22, 2014 1 Review 2 3 4 Mixing time I Theorem (Convergence to stationarity) Consider a finite

More information

Mean-field dual of cooperative reproduction

Mean-field dual of cooperative reproduction The mean-field dual of systems with cooperative reproduction joint with Tibor Mach (Prague) A. Sturm (Göttingen) Friday, July 6th, 2018 Poisson construction of Markov processes Let (X t ) t 0 be a continuous-time

More information

Concentration, self-bounding functions

Concentration, self-bounding functions Concentration, self-bounding functions S. Boucheron 1 and G. Lugosi 2 and P. Massart 3 1 Laboratoire de Probabilités et Modèles Aléatoires Université Paris-Diderot 2 Economics University Pompeu Fabra 3

More information

Concentration of Measures by Bounded Size Bias Couplings

Concentration of Measures by Bounded Size Bias Couplings Concentration of Measures by Bounded Size Bias Couplings Subhankar Ghosh, Larry Goldstein University of Southern California [arxiv:0906.3886] January 10 th, 2013 Concentration of Measure Distributional

More information

Stat 516, Homework 1

Stat 516, Homework 1 Stat 516, Homework 1 Due date: October 7 1. Consider an urn with n distinct balls numbered 1,..., n. We sample balls from the urn with replacement. Let N be the number of draws until we encounter a ball

More information

2. Variance and Covariance: We will now derive some classic properties of variance and covariance. Assume real-valued random variables X and Y.

2. Variance and Covariance: We will now derive some classic properties of variance and covariance. Assume real-valued random variables X and Y. CS450 Final Review Problems Fall 08 Solutions or worked answers provided Problems -6 are based on the midterm review Identical problems are marked recap] Please consult previous recitations and textbook

More information

Generative Models and Stochastic Algorithms for Population Average Estimation and Image Analysis

Generative Models and Stochastic Algorithms for Population Average Estimation and Image Analysis Generative Models and Stochastic Algorithms for Population Average Estimation and Image Analysis Stéphanie Allassonnière CIS, JHU July, 15th 28 Context : Computational Anatomy Context and motivations :

More information

Tasmanian School of Business & Economics Economics & Finance Seminar Series 1 February 2016

Tasmanian School of Business & Economics Economics & Finance Seminar Series 1 February 2016 P A R X (PARX), US A A G C D K A R Gruppo Bancario Credito Valtellinese, University of Bologna, University College London and University of Copenhagen Tasmanian School of Business & Economics Economics

More information

MAT 135B Midterm 1 Solutions

MAT 135B Midterm 1 Solutions MAT 35B Midterm Solutions Last Name (PRINT): First Name (PRINT): Student ID #: Section: Instructions:. Do not open your test until you are told to begin. 2. Use a pen to print your name in the spaces above.

More information

E X A M. Probability Theory and Stochastic Processes Date: December 13, 2016 Duration: 4 hours. Number of pages incl.

E X A M. Probability Theory and Stochastic Processes Date: December 13, 2016 Duration: 4 hours. Number of pages incl. E X A M Course code: Course name: Number of pages incl. front page: 6 MA430-G Probability Theory and Stochastic Processes Date: December 13, 2016 Duration: 4 hours Resources allowed: Notes: Pocket calculator,

More information

STAT 200C: High-dimensional Statistics

STAT 200C: High-dimensional Statistics STAT 200C: High-dimensional Statistics Arash A. Amini April 27, 2018 1 / 80 Classical case: n d. Asymptotic assumption: d is fixed and n. Basic tools: LLN and CLT. High-dimensional setting: n d, e.g. n/d

More information

Useful Probability Theorems

Useful Probability Theorems Useful Probability Theorems Shiu-Tang Li Finished: March 23, 2013 Last updated: November 2, 2013 1 Convergence in distribution Theorem 1.1. TFAE: (i) µ n µ, µ n, µ are probability measures. (ii) F n (x)

More information

Upper Bound for Intermediate Singular Values of Random Sub-Gaussian Matrices 1

Upper Bound for Intermediate Singular Values of Random Sub-Gaussian Matrices 1 Upper Bound for Intermediate Singular Values of Random Sub-Gaussian Matrices 1 Feng Wei 2 University of Michigan July 29, 2016 1 This presentation is based a project under the supervision of M. Rudelson.

More information

Brownian Motion. 1 Definition Brownian Motion Wiener measure... 3

Brownian Motion. 1 Definition Brownian Motion Wiener measure... 3 Brownian Motion Contents 1 Definition 2 1.1 Brownian Motion................................. 2 1.2 Wiener measure.................................. 3 2 Construction 4 2.1 Gaussian process.................................

More information

On the Bennett-Hoeffding inequality

On the Bennett-Hoeffding inequality On the Bennett-Hoeffding inequality Iosif 1,2,3 1 Department of Mathematical Sciences Michigan Technological University 2 Supported by NSF grant DMS-0805946 3 Paper available at http://arxiv.org/abs/0902.4058

More information

Exercises: sheet 1. k=1 Y k is called compound Poisson process (X t := 0 if N t = 0).

Exercises: sheet 1. k=1 Y k is called compound Poisson process (X t := 0 if N t = 0). Exercises: sheet 1 1. Prove: Let X be Poisson(s) and Y be Poisson(t) distributed. If X and Y are independent, then X + Y is Poisson(t + s) distributed (t, s > 0). This means that the property of a convolution

More information

Stable Lévy motion with values in the Skorokhod space: construction and approximation

Stable Lévy motion with values in the Skorokhod space: construction and approximation Stable Lévy motion with values in the Skorokhod space: construction and approximation arxiv:1809.02103v1 [math.pr] 6 Sep 2018 Raluca M. Balan Becem Saidani September 5, 2018 Abstract In this article, we

More information

Regeneration-based statistics for Harris recurrent Markov chains

Regeneration-based statistics for Harris recurrent Markov chains 1 Regeneration-based statistics for Harris recurrent Markov chains Patrice Bertail 1 and Stéphan Clémençon 2 1 CREST-LS, 3, ave Pierre Larousse, 94205 Malakoff, France Patrice.Bertail@ensae.fr 2 MODAL

More information

Essentials on the Analysis of Randomized Algorithms

Essentials on the Analysis of Randomized Algorithms Essentials on the Analysis of Randomized Algorithms Dimitris Diochnos Feb 0, 2009 Abstract These notes were written with Monte Carlo algorithms primarily in mind. Topics covered are basic (discrete) random

More information

Local consistency of Markov chain Monte Carlo methods

Local consistency of Markov chain Monte Carlo methods Ann Inst Stat Math (2014) 66:63 74 DOI 10.1007/s10463-013-0403-3 Local consistency of Markov chain Monte Carlo methods Kengo Kamatani Received: 12 January 2012 / Revised: 8 March 2013 / Published online:

More information

Practical unbiased Monte Carlo for Uncertainty Quantification

Practical unbiased Monte Carlo for Uncertainty Quantification Practical unbiased Monte Carlo for Uncertainty Quantification Sergios Agapiou Department of Statistics, University of Warwick MiR@W day: Uncertainty in Complex Computer Models, 2nd February 2015, University

More information

Estimation of arrival and service rates for M/M/c queue system

Estimation of arrival and service rates for M/M/c queue system Estimation of arrival and service rates for M/M/c queue system Katarína Starinská starinskak@gmail.com Charles University Faculty of Mathematics and Physics Department of Probability and Mathematical Statistics

More information

Spring 2012 Math 541B Exam 1

Spring 2012 Math 541B Exam 1 Spring 2012 Math 541B Exam 1 1. A sample of size n is drawn without replacement from an urn containing N balls, m of which are red and N m are black; the balls are otherwise indistinguishable. Let X denote

More information

Lecture 5: Asymptotic Equipartition Property

Lecture 5: Asymptotic Equipartition Property Lecture 5: Asymptotic Equipartition Property Law of large number for product of random variables AEP and consequences Dr. Yao Xie, ECE587, Information Theory, Duke University Stock market Initial investment

More information

Large deviations of empirical processes

Large deviations of empirical processes Large deviations of empirical processes Miguel A. Arcones Abstract. We give necessary and sufficient conditions for the large deviations of empirical processes and of Banach space valued random vectors.

More information

Mixing time for a random walk on a ring

Mixing time for a random walk on a ring Mixing time for a random walk on a ring Stephen Connor Joint work with Michael Bate Paris, September 2013 Introduction Let X be a discrete time Markov chain on a finite state space S, with transition matrix

More information

The simple slice sampler is a specialised type of MCMC auxiliary variable method (Swendsen and Wang, 1987; Edwards and Sokal, 1988; Besag and Green, 1

The simple slice sampler is a specialised type of MCMC auxiliary variable method (Swendsen and Wang, 1987; Edwards and Sokal, 1988; Besag and Green, 1 Recent progress on computable bounds and the simple slice sampler by Gareth O. Roberts* and Jerey S. Rosenthal** (May, 1999.) This paper discusses general quantitative bounds on the convergence rates of

More information

Lecture Notes 5 Convergence and Limit Theorems. Convergence with Probability 1. Convergence in Mean Square. Convergence in Probability, WLLN

Lecture Notes 5 Convergence and Limit Theorems. Convergence with Probability 1. Convergence in Mean Square. Convergence in Probability, WLLN Lecture Notes 5 Convergence and Limit Theorems Motivation Convergence with Probability Convergence in Mean Square Convergence in Probability, WLLN Convergence in Distribution, CLT EE 278: Convergence and

More information

Quantitative Non-Geometric Convergence Bounds for Independence Samplers

Quantitative Non-Geometric Convergence Bounds for Independence Samplers Quantitative Non-Geometric Convergence Bounds for Independence Samplers by Gareth O. Roberts * and Jeffrey S. Rosenthal ** (September 28; revised July 29.) 1. Introduction. Markov chain Monte Carlo (MCMC)

More information

Mathematics Qualifying Examination January 2015 STAT Mathematical Statistics

Mathematics Qualifying Examination January 2015 STAT Mathematical Statistics Mathematics Qualifying Examination January 2015 STAT 52800 - Mathematical Statistics NOTE: Answer all questions completely and justify your derivations and steps. A calculator and statistical tables (normal,

More information

Exercises in Extreme value theory

Exercises in Extreme value theory Exercises in Extreme value theory 2016 spring semester 1. Show that L(t) = logt is a slowly varying function but t ǫ is not if ǫ 0. 2. If the random variable X has distribution F with finite variance,

More information

Statistical Machine Learning

Statistical Machine Learning Statistical Machine Learning UoC Stats 37700, Winter quarter Lecture 2: Introduction to statistical learning theory. 1 / 22 Goals of statistical learning theory SLT aims at studying the performance of

More information

Entropy and Ergodic Theory Lecture 15: A first look at concentration

Entropy and Ergodic Theory Lecture 15: A first look at concentration Entropy and Ergodic Theory Lecture 15: A first look at concentration 1 Introduction to concentration Let X 1, X 2,... be i.i.d. R-valued RVs with common distribution µ, and suppose for simplicity that

More information

Deviations from the Mean

Deviations from the Mean Deviations from the Mean The Markov inequality for non-negative RVs Variance Definition The Bienaymé Inequality For independent RVs The Chebyeshev Inequality Markov s Inequality For any non-negative random

More information

Tail bound inequalities and empirical likelihood for the mean

Tail bound inequalities and empirical likelihood for the mean Tail bound inequalities and empirical likelihood for the mean Sandra Vucane 1 1 University of Latvia, Riga 29 th of September, 2011 Sandra Vucane (LU) Tail bound inequalities and EL for the mean 29.09.2011

More information

Lecture 3 Stationary Processes and the Ergodic LLN (Reference Section 2.2, Hayashi)

Lecture 3 Stationary Processes and the Ergodic LLN (Reference Section 2.2, Hayashi) Lecture 3 Stationary Processes and the Ergodic LLN (Reference Section 2.2, Hayashi) Our immediate goal is to formulate an LLN and a CLT which can be applied to establish sufficient conditions for the consistency

More information

Probability Theory II. Spring 2016 Peter Orbanz

Probability Theory II. Spring 2016 Peter Orbanz Probability Theory II Spring 2016 Peter Orbanz Contents Chapter 1. Martingales 1 1.1. Martingales indexed by partially ordered sets 1 1.2. Martingales from adapted processes 4 1.3. Stopping times and

More information

Stein s Method: Distributional Approximation and Concentration of Measure

Stein s Method: Distributional Approximation and Concentration of Measure Stein s Method: Distributional Approximation and Concentration of Measure Larry Goldstein University of Southern California 36 th Midwest Probability Colloquium, 2014 Concentration of Measure Distributional

More information

) ) = γ. and P ( X. B(a, b) = Γ(a)Γ(b) Γ(a + b) ; (x + y, ) I J}. Then, (rx) a 1 (ry) b 1 e (x+y)r r 2 dxdy Γ(a)Γ(b) D

) ) = γ. and P ( X. B(a, b) = Γ(a)Γ(b) Γ(a + b) ; (x + y, ) I J}. Then, (rx) a 1 (ry) b 1 e (x+y)r r 2 dxdy Γ(a)Γ(b) D 3 Independent Random Variables II: Examples 3.1 Some functions of independent r.v. s. Let X 1, X 2,... be independent r.v. s with the known distributions. Then, one can compute the distribution of a r.v.

More information

An introduction to adaptive MCMC

An introduction to adaptive MCMC An introduction to adaptive MCMC Gareth Roberts MIRAW Day on Monte Carlo methods March 2011 Mainly joint work with Jeff Rosenthal. http://www2.warwick.ac.uk/fac/sci/statistics/crism/ Conferences and workshops

More information