Theoretical Statistics. Lecture 12.
|
|
- Marylou Andrews
- 5 years ago
- Views:
Transcription
1 Theoretical Statistics. Lecture 12. Peter Bartlett Uniform laws of large numbers: Bounding Rademacher complexity. 1. Metric entropy. 2. Canonical Rademacher and Gaussian processes 1
2 Recall: Covering numbers A pseudometric is like a metric, but we don t insist that d(x,y) = 0 impliesx = y. Definition: Anǫ-cover of a subsett of a pseudometric space(s,d) is a set ˆT T such that for each t T there is a ˆt ˆT such that d(t,ˆt) ǫ. The ǫ-covering number of T is N(ǫ,T,d) = min{ ˆT : ˆT is an ǫ-cover oft}. A set T is totally bounded if, for all ǫ > 0, N(ǫ,T,d) <. The function ǫ log N(ǫ, T, d) is the metric entropy of T. If lim ǫ 0 logn(ǫ)/log(1/ǫ) exists, it is called the metric dimension. 2
3 Covering numbers Intuition: A d-dimensional set has metric dimension d. (N(ǫ) = Θ(1/ǫ d ).) Example: ([0,1] d,l ) hasn(ǫ) = Θ(1/ǫ d ). 3
4 Packing numbers Definition: An ǫ-packing of a subset T of a pseudometric space (S,d) is a subset ˆT T such that each pair s, t ˆT satisfies d(s, t) > ǫ. The ǫ-packing number oft is M(ǫ,T,d) = max{ ˆT : ˆT is anǫ-packing oft}. 4
5 Covering and packing numbers Theorem: For all ǫ > 0,M(2ǫ) N(ǫ) M(ǫ). Thus, the scaling of the covering and packing numbers is the same. 5
6 Covering and packing numbers: Proof For the first inequality, consider a minimal ǫ-cover ˆT. Any two elements of a2ǫ-packing oft cannot be withinǫof the same element of ˆT. (Otherwise, the triangle inequality shows that they are within2ǫ of each other.) Thus, there can be no more than one element of a2ǫ packing for each of the N(ǫ) elements of ˆT. That is,m(2ǫ) N(ǫ). For the second inequality, consider an ǫ-packing ˆT of size M(ǫ). Since it is maximal, no other point s T can be added for which some t ˆT has d(s,t) > ǫ. Thus, ˆT is anǫ-cover. So the minimal ǫ-cover has size N(ǫ) M(ǫ). 6
7 Covering and packing numbers: Example Theorem: Let be a norm onr d and let B be the unit ball. Then 1 ǫ d N(ǫ,B, ) ( ) d 2 ǫ +1. 7
8 Covering and packing numbers of a norm ball: Proof Lower bound: Consider an ǫ-cover {x 1,...,x N } of sizen = N(ǫ,B), and notice that so N B (x i +ǫb), i=1 vol(b) N(ǫ,B)vol(ǫB) = N(ǫ,B)ǫ d vol(b), and hence N(ǫ,B) 1/ǫ d. 8
9 Covering and packing numbers of a norm ball: Proof Upper bound: Consider a maximal ǫ-packing {x 1,...,x M } of size M = M(ǫ,B). Since it s a packing, the ballsx i +(ǫ/2)b are disjoint. Each of these balls is contained in(1+ǫ/2)b. Thus, so M i=1 (x i + ǫ 2 B ) (1+ǫ/2)B, Mvol((ǫ/2)B) vol((1+ǫ/2)b) ( ǫ dvol(b) ( M 1+ 2) 2) ǫ dvol(b). and hence N(ǫ,B) M(ǫ,B) (2/ǫ+1) d. 9
10 Example: smoothly parameterized functions Let F be a parameterized class of functions, F = {f(θ, ) : θ Θ}. Let Θ be a norm onθand let F be a norm onf. Suppose that the mapping θ f(θ, ) is L-Lipschitz, that is, f(θ, ) f(θ, ) F L θ θ Θ. Then N(ǫ,F, F ) N(ǫ/L,Θ, Θ ). 10
11 Example: smoothly parameterized functions A Lipschitz parameterization allows us to translates a cover of the parameter space into a cover of the function space. Example: If F is smoothly parameterized by a (compact set of) d parameters, then N(ǫ,F) = O(1/ǫ d ). 11
12 Example: 1-dimensional Lipschitz functions LetF be the set ofl-lipschitz functions mapping from[0,1] to[0,1]. Then in the infinity norm f = sup x [0,1] f(x), logn(ǫ,f, ) = Θ(L/ǫ). Proof idea: form an ǫ grid of the y-axis, and anǫ/l grid of the x-axis, and consider all functions that are piecewise linear on this grid, where all pieces have slopes+l or L. There are 1/ǫ starting points, and for each starting point there are 2 L/ǫ slope choices. It s easy to show that this set is ano(ǫ) packing and ano(ǫ) cover. 12
13 Example: d-dimensional Lipschitz functions Let F d be the set of L-Lipschitz functions (wrt ) mapping from[0,1] d to[0, 1]. Then logn(ǫ,f d, ) = Θ ( (L/ǫ) d). Note the exponential dependence on the dimension. 13
14 Canonical Rademacher and Gaussian Processes Definition: Fix a set T R n. 1. The canonical Gaussian process is the stochastic process G θ = g,θ = n g i θ i, i=1 where g i N(0,1) i.i.d. 2. The canonical Rademacher process is the stochastic process R θ = ǫ,θ = n ǫ i θ i, i=1 where theǫ i are i.i.d. and uniform on{±1}. 14
15 Canonical Rademacher and Gaussian Processes Definition: A stochastic process θ X θ with indexing set T is sub- Gaussian with respect to a metric d ont if, for all θ,θ T and all λ R, ( λ Eexp(λ(X θ X θ )) 2 d(θ,θ ) 2 ) exp. 2 The canonical Rademacher and Gaussian processes are sub-gaussian wrt the Euclidean metric. 15
16 Canonical Rademacher and Gaussian Processes Indeed: G θ G θ = g,θ θ, which isn(0, θ θ 2 ), and hence its moment generating function is equal to the upper bound. R θ R θ = ǫ,θ θ, which, by the bounded differences property, is sub-gaussian with parameter θ θ 2. 16
17 An aside: Orlicz norms Definition: For1 α 2, the α-orlicz norm of a random variable X is { ( ) } X α X ψα = inf C > 0 : Eexp 2. C α Theorem: There are constants c 1,c 2 such that, for all X and all t 1, ( ) t α Pr( X t) 2exp c 1 X α ψ α and conversely, Pr( X t) cexp( t α /K α ) implies X ψα c 2 K. Sub-Gaussian means X θ X θ ψ 2 Ld(θ,θ )., 17
18 Canonical Gaussian and Rademacher processes Theorem: ForT R n, Esup θ T R θ π 2 Esup G θ c lognesupr θ. θ T θ T 18
19 Canonical Gaussian and Rademacher processes Proof of first inequality: Esup θ T G θ = Esup θ T = Esup θ T n g i θ i i=1 n ǫ i g i θ i i=1 n Esup ǫ i E[ g i ]θ i θ T i=1 2 = π Esup R θ. θ T 19
20 Canonical Gaussian and Rademacher processes: Example ForΘthe l 1 -ball inr n, Esup ǫ,θ = E ǫ = 1. θ [where we ve used the duality ofl 1 and l (equivalently, that Hölder s inequality is tight).] Also, Esup g,θ = E g 2lnn. θ The Gaussian and Rademacher complexities are a logn factor apart in this case. 20
21 Canonical Gaussian and Rademacher processes: Example To see the last inequality, we generalize the Finite Lemma to the sub-gaussian case: Lemma: Forg with independent sub-gaussian components, Emax g,a max a 2log A. a A a A In this case, A = {e i : 1 i n}, so max a A a = 1 and A = n. 21
22 Canonical Gaussian and Rademacher processes: Example Proof: exp ( ) λemax g,a a A Eexp ( ) λmax g,a a A = Emax a A exp(λ g,a ) a AEexp(λ g,a ) A exp ( λ 2 R 2 /2 ), since g i is sub-gaussian (here, R 2 = max a A a 2 2). Picking λ 2 = 2log A /R 2 gives the result. 22
Theoretical Statistics. Lecture 14.
Theoretical Statistics. Lecture 14. Peter Bartlett Metric entropy. 1. Chaining: Dudley s entropy integral 1 Recall: Sub-Gaussian processes Definition: A stochastic process θ X θ with indexing set T is
More informationSolutions to Problem Set 5 for , Fall 2007
Solutions to Problem Set 5 for 18.101, Fall 2007 1 Exercise 1 Solution For the counterexample, let us consider M = (0, + ) and let us take V = on M. x Let W be the vector field on M that is identically
More information21.1 Lower bounds on minimax risk for functional estimation
ECE598: Information-theoretic methods in high-dimensional statistics Spring 016 Lecture 1: Functional estimation & testing Lecturer: Yihong Wu Scribe: Ashok Vardhan, Apr 14, 016 In this chapter, we will
More informationTheoretical Statistics. Lecture 1.
1. Organizational issues. 2. Overview. 3. Stochastic convergence. Theoretical Statistics. Lecture 1. eter Bartlett 1 Organizational Issues Lectures: Tue/Thu 11am 12:30pm, 332 Evans. eter Bartlett. bartlett@stat.
More informationLARGE DEVIATIONS OF TYPICAL LINEAR FUNCTIONALS ON A CONVEX BODY WITH UNCONDITIONAL BASIS. S. G. Bobkov and F. L. Nazarov. September 25, 2011
LARGE DEVIATIONS OF TYPICAL LINEAR FUNCTIONALS ON A CONVEX BODY WITH UNCONDITIONAL BASIS S. G. Bobkov and F. L. Nazarov September 25, 20 Abstract We study large deviations of linear functionals on an isotropic
More informationLecture 6: September 19
36-755: Advanced Statistical Theory I Fall 2016 Lecture 6: September 19 Lecturer: Alessandro Rinaldo Scribe: YJ Choe Note: LaTeX template courtesy of UC Berkeley EECS dept. Disclaimer: These notes have
More informationThe Uniform Weak Law of Large Numbers and the Consistency of M-Estimators of Cross-Section and Time Series Models
The Uniform Weak Law of Large Numbers and the Consistency of M-Estimators of Cross-Section and Time Series Models Herman J. Bierens Pennsylvania State University September 16, 2005 1. The uniform weak
More informationLecture 35: December The fundamental statistical distances
36-705: Intermediate Statistics Fall 207 Lecturer: Siva Balakrishnan Lecture 35: December 4 Today we will discuss distances and metrics between distributions that are useful in statistics. I will be lose
More informationFunctional Analysis Exercise Class
Functional Analysis Exercise Class Week 2 November 6 November Deadline to hand in the homeworks: your exercise class on week 9 November 13 November Exercises (1) Let X be the following space of piecewise
More informationDuality of multiparameter Hardy spaces H p on spaces of homogeneous type
Duality of multiparameter Hardy spaces H p on spaces of homogeneous type Yongsheng Han, Ji Li, and Guozhen Lu Department of Mathematics Vanderbilt University Nashville, TN Internet Analysis Seminar 2012
More informationδ xj β n = 1 n Theorem 1.1. The sequence {P n } satisfies a large deviation principle on M(X) with the rate function I(β) given by
. Sanov s Theorem Here we consider a sequence of i.i.d. random variables with values in some complete separable metric space X with a common distribution α. Then the sample distribution β n = n maps X
More information4 Expectation & the Lebesgue Theorems
STA 205: Probability & Measure Theory Robert L. Wolpert 4 Expectation & the Lebesgue Theorems Let X and {X n : n N} be random variables on a probability space (Ω,F,P). If X n (ω) X(ω) for each ω Ω, does
More informationA glimpse into convex geometry. A glimpse into convex geometry
A glimpse into convex geometry 5 \ þ ÏŒÆ Two basis reference: 1. Keith Ball, An elementary introduction to modern convex geometry 2. Chuanming Zong, What is known about unit cubes Convex geometry lies
More informationMATH 51H Section 4. October 16, Recall what it means for a function between metric spaces to be continuous:
MATH 51H Section 4 October 16, 2015 1 Continuity Recall what it means for a function between metric spaces to be continuous: Definition. Let (X, d X ), (Y, d Y ) be metric spaces. A function f : X Y is
More informationEcon Lecture 3. Outline. 1. Metric Spaces and Normed Spaces 2. Convergence of Sequences in Metric Spaces 3. Sequences in R and R n
Econ 204 2011 Lecture 3 Outline 1. Metric Spaces and Normed Spaces 2. Convergence of Sequences in Metric Spaces 3. Sequences in R and R n 1 Metric Spaces and Metrics Generalize distance and length notions
More informationLecture 18: March 15
CS71 Randomness & Computation Spring 018 Instructor: Alistair Sinclair Lecture 18: March 15 Disclaimer: These notes have not been subjected to the usual scrutiny accorded to formal publications. They may
More informationNotes on Gaussian processes and majorizing measures
Notes on Gaussian processes and majorizing measures James R. Lee 1 Gaussian processes Consider a Gaussian process {X t } for some index set T. This is a collection of jointly Gaussian random variables,
More informationAn elementary proof of the weak convergence of empirical processes
An elementary proof of the weak convergence of empirical processes Dragan Radulović Department of Mathematics, Florida Atlantic University Marten Wegkamp Department of Mathematics & Department of Statistical
More informationMath 201 Handout 1. Rich Schwartz. September 6, 2006
Math 21 Handout 1 Rich Schwartz September 6, 26 The purpose of this handout is to give a proof of the basic existence and uniqueness result for ordinary differential equations. This result includes the
More informationLecture 5 - Hausdorff and Gromov-Hausdorff Distance
Lecture 5 - Hausdorff and Gromov-Hausdorff Distance August 1, 2011 1 Definition and Basic Properties Given a metric space X, the set of closed sets of X supports a metric, the Hausdorff metric. If A is
More informationIsodiametric problem in Carnot groups
Conference Geometric Measure Theory Université Paris Diderot, 12th-14th September 2012 Isodiametric inequality in R n Isodiametric inequality: where ω n = L n (B(0, 1)). L n (A) 2 n ω n (diam A) n Isodiametric
More informationLecture 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 informationChapter 14. Duality for Normed Linear Spaces
14.1. Linear Functionals, Bounded Linear Functionals, and Weak Topologies 1 Chapter 14. Duality for Normed Linear Spaces Note. In Section 8.1, we defined a linear functional on a normed linear space, a
More informationLinear Analysis Lecture 5
Linear Analysis Lecture 5 Inner Products and V Let dim V < with inner product,. Choose a basis B and let v, w V have coordinates in F n given by x 1. x n and y 1. y n, respectively. Let A F n n be the
More informationTheoretical Statistics. Lecture 17.
Theoretical Statistics. Lecture 17. Peter Bartlett 1. Asymptotic normality of Z-estimators: classical conditions. 2. Asymptotic equicontinuity. 1 Recall: Delta method Theorem: Supposeφ : R k R m is differentiable
More informationReal Analysis Math 125A, Fall 2012 Sample Final Questions. x 1+x y. x y x. 2 (1+x 2 )(1+y 2 ) x y
. Define f : R R by Real Analysis Math 25A, Fall 202 Sample Final Questions f() = 3 + 2. Show that f is continuous on R. Is f uniformly continuous on R? To simplify the inequalities a bit, we write 3 +
More informationTopological properties of Z p and Q p and Euclidean models
Topological properties of Z p and Q p and Euclidean models Samuel Trautwein, Esther Röder, Giorgio Barozzi November 3, 20 Topology of Q p vs Topology of R Both R and Q p are normed fields and complete
More information7 Influence Functions
7 Influence Functions The influence function is used to approximate the standard error of a plug-in estimator. The formal definition is as follows. 7.1 Definition. The Gâteaux derivative of T at F in the
More informationBasic Properties of Metric and Normed Spaces
Basic Properties of Metric and Normed Spaces Computational and Metric Geometry Instructor: Yury Makarychev The second part of this course is about metric geometry. We will study metric spaces, low distortion
More informationConstrained optimization
Constrained optimization DS-GA 1013 / MATH-GA 2824 Optimization-based Data Analysis http://www.cims.nyu.edu/~cfgranda/pages/obda_fall17/index.html Carlos Fernandez-Granda Compressed sensing Convex constrained
More informationis a Borel subset of S Θ for each c R (Bertsekas and Shreve, 1978, Proposition 7.36) This always holds in practical applications.
Stat 811 Lecture Notes The Wald Consistency Theorem Charles J. Geyer April 9, 01 1 Analyticity Assumptions Let { f θ : θ Θ } be a family of subprobability densities 1 with respect to a measure µ on a measurable
More informationl 1 -Regularized Linear Regression: Persistence and Oracle Inequalities
l -Regularized Linear Regression: Persistence and Oracle Inequalities Peter Bartlett EECS and Statistics UC Berkeley slides at http://www.stat.berkeley.edu/ bartlett Joint work with Shahar Mendelson and
More informationMeasure and Integration: Solutions of CW2
Measure and Integration: s of CW2 Fall 206 [G. Holzegel] December 9, 206 Problem of Sheet 5 a) Left (f n ) and (g n ) be sequences of integrable functions with f n (x) f (x) and g n (x) g (x) for almost
More information10-704: Information Processing and Learning Spring Lecture 8: Feb 5
10-704: Information Processing and Learning Spring 2015 Lecture 8: Feb 5 Lecturer: Aarti Singh Scribe: Siheng Chen Disclaimer: These notes have not been subjected to the usual scrutiny reserved for formal
More informationExistence and uniqueness of solutions for nonlinear ODEs
Chapter 4 Existence and uniqueness of solutions for nonlinear ODEs In this chapter we consider the existence and uniqueness of solutions for the initial value problem for general nonlinear ODEs. Recall
More informationLecture 2: Uniform Entropy
STAT 583: Advanced Theory of Statistical Inference Spring 218 Lecture 2: Uniform Entropy Lecturer: Fang Han April 16 Disclaimer: These notes have not been subjected to the usual scrutiny reserved for formal
More informationNonlinear Control Systems
Nonlinear Control Systems António Pedro Aguiar pedro@isr.ist.utl.pt 3. Fundamental properties IST-DEEC PhD Course http://users.isr.ist.utl.pt/%7epedro/ncs2012/ 2012 1 Example Consider the system ẋ = f
More informationCS229T/STATS231: Statistical Learning Theory. Lecturer: Tengyu Ma Lecture 11 Scribe: Jongho Kim, Jamie Kang October 29th, 2018
CS229T/STATS231: Statistical Learning Theory Lecturer: Tengyu Ma Lecture 11 Scribe: Jongho Kim, Jamie Kang October 29th, 2018 1 Overview This lecture mainly covers Recall the statistical theory of GANs
More informationFast Rates for Estimation Error and Oracle Inequalities for Model Selection
Fast Rates for Estimation Error and Oracle Inequalities for Model Selection Peter L. Bartlett Computer Science Division and Department of Statistics University of California, Berkeley bartlett@cs.berkeley.edu
More informationDraft. Advanced Probability Theory (Fall 2017) J.P.Kim Dept. of Statistics. Finally modified at November 28, 2017
Fall 207 Dept. of Statistics Finally modified at November 28, 207 Preface & Disclaimer This note is a summary of the lecture Advanced Probability Theory 326.729A held at Seoul National University, Fall
More informationAn introduction to some aspects of functional analysis
An introduction to some aspects of functional analysis Stephen Semmes Rice University Abstract These informal notes deal with some very basic objects in functional analysis, including norms and seminorms
More informationThe Moment Method; Convex Duality; and Large/Medium/Small Deviations
Stat 928: Statistical Learning Theory Lecture: 5 The Moment Method; Convex Duality; and Large/Medium/Small Deviations Instructor: Sham Kakade The Exponential Inequality and Convex Duality The exponential
More informationLecture 3. Econ August 12
Lecture 3 Econ 2001 2015 August 12 Lecture 3 Outline 1 Metric and Metric Spaces 2 Norm and Normed Spaces 3 Sequences and Subsequences 4 Convergence 5 Monotone and Bounded Sequences Announcements: - Friday
More informationIntroduction to Empirical Processes and Semiparametric Inference Lecture 12: Glivenko-Cantelli and Donsker Results
Introduction to Empirical Processes and Semiparametric Inference Lecture 12: Glivenko-Cantelli and Donsker Results Michael R. Kosorok, Ph.D. Professor and Chair of Biostatistics Professor of Statistics
More informationl(y j ) = 0 for all y j (1)
Problem 1. The closed linear span of a subset {y j } of a normed vector space is defined as the intersection of all closed subspaces containing all y j and thus the smallest such subspace. 1 Show that
More informationPCA with random noise. Van Ha Vu. Department of Mathematics Yale University
PCA with random noise Van Ha Vu Department of Mathematics Yale University An important problem that appears in various areas of applied mathematics (in particular statistics, computer science and numerical
More informationAnalysis Comprehensive Exam Questions Fall F(x) = 1 x. f(t)dt. t 1 2. tf 2 (t)dt. and g(t, x) = 2 t. 2 t
Analysis Comprehensive Exam Questions Fall 2. Let f L 2 (, ) be given. (a) Prove that ( x 2 f(t) dt) 2 x x t f(t) 2 dt. (b) Given part (a), prove that F L 2 (, ) 2 f L 2 (, ), where F(x) = x (a) Using
More informationVectors. January 13, 2013
Vectors January 13, 2013 The simplest tensors are scalars, which are the measurable quantities of a theory, left invariant by symmetry transformations. By far the most common non-scalars are the vectors,
More informationLecture 9: October 25, Lower bounds for minimax rates via multiple hypotheses
Information and Coding Theory Autumn 07 Lecturer: Madhur Tulsiani Lecture 9: October 5, 07 Lower bounds for minimax rates via multiple hypotheses In this lecture, we extend the ideas from the previous
More informationKernel Density Estimation
EECS 598: Statistical Learning Theory, Winter 2014 Topic 19 Kernel Density Estimation Lecturer: Clayton Scott Scribe: Yun Wei, Yanzhen Deng Disclaimer: These notes have not been subjected to the usual
More informationStat 260/CS Learning in Sequential Decision Problems. Peter Bartlett
Stat 260/CS 294-102. Learning in Sequential Decision Problems. Peter Bartlett 1. Multi-armed bandit algorithms. Concentration inequalities. P(X ǫ) exp( ψ (ǫ))). Cumulant generating function bounds. Hoeffding
More informationEMPIRICAL PROCESSES: Theory and Applications
Corso estivo di statistica e calcolo delle probabilità EMPIRICAL PROCESSES: Theory and Applications Torgnon, 23 Corrected Version, 2 July 23; 21 August 24 Jon A. Wellner University of Washington Statistics,
More informationPROBLEMS. (b) (Polarization Identity) Show that in any inner product space
1 Professor Carl Cowen Math 54600 Fall 09 PROBLEMS 1. (Geometry in Inner Product Spaces) (a) (Parallelogram Law) Show that in any inner product space x + y 2 + x y 2 = 2( x 2 + y 2 ). (b) (Polarization
More informationMath 421, Homework #9 Solutions
Math 41, Homework #9 Solutions (1) (a) A set E R n is said to be path connected if for any pair of points x E and y E there exists a continuous function γ : [0, 1] R n satisfying γ(0) = x, γ(1) = y, and
More informationPhase Transitions for Dilute Particle Systems with Lennard-Jones Potential
Weierstrass Institute for Applied Analysis and Stochastics Phase Transitions for Dilute Particle Systems with Lennard-Jones Potential Wolfgang König TU Berlin and WIAS joint with Andrea Collevecchio (Venice),
More informationProblem Set 2: Solutions Math 201A: Fall 2016
Problem Set 2: s Math 201A: Fall 2016 Problem 1. (a) Prove that a closed subset of a complete metric space is complete. (b) Prove that a closed subset of a compact metric space is compact. (c) Prove that
More informationApplied Analysis (APPM 5440): Final exam 1:30pm 4:00pm, Dec. 14, Closed books.
Applied Analysis APPM 44: Final exam 1:3pm 4:pm, Dec. 14, 29. Closed books. Problem 1: 2p Set I = [, 1]. Prove that there is a continuous function u on I such that 1 ux 1 x sin ut 2 dt = cosx, x I. Define
More informationSTAT 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 informationSobolevology. 1. Definitions and Notation. When α = 1 this seminorm is the same as the Lipschitz constant of the function f. 2.
Sobolevology 1. Definitions and Notation 1.1. The domain. is an open subset of R n. 1.2. Hölder seminorm. For α (, 1] the Hölder seminorm of exponent α of a function is given by f(x) f(y) [f] α = sup x
More informationLECTURE 15: COMPLETENESS AND CONVEXITY
LECTURE 15: COMPLETENESS AND CONVEXITY 1. The Hopf-Rinow Theorem Recall that a Riemannian manifold (M, g) is called geodesically complete if the maximal defining interval of any geodesic is R. On the other
More informationAn Algorithmist s Toolkit Nov. 10, Lecture 17
8.409 An Algorithmist s Toolkit Nov. 0, 009 Lecturer: Jonathan Kelner Lecture 7 Johnson-Lindenstrauss Theorem. Recap We first recap a theorem (isoperimetric inequality) and a lemma (concentration) from
More informationLecture Learning infinite hypothesis class via VC-dimension and Rademacher complexity;
CSCI699: Topics in Learning and Game Theory Lecture 2 Lecturer: Ilias Diakonikolas Scribes: Li Han Today we will cover the following 2 topics: 1. Learning infinite hypothesis class via VC-dimension and
More informationSteiner s formula and large deviations theory
Steiner s formula and large deviations theory Venkat Anantharam EECS Department University of California, Berkeley May 19, 2015 Simons Conference on Networks and Stochastic Geometry Blanton Museum of Art
More informationThe Dirichlet s P rinciple. In this lecture we discuss an alternative formulation of the Dirichlet problem for the Laplace equation:
Oct. 1 The Dirichlet s P rinciple In this lecture we discuss an alternative formulation of the Dirichlet problem for the Laplace equation: 1. Dirichlet s Principle. u = in, u = g on. ( 1 ) If we multiply
More informationn E(X t T n = lim X s Tn = X s
Stochastic Calculus Example sheet - Lent 15 Michael Tehranchi Problem 1. Let X be a local martingale. Prove that X is a uniformly integrable martingale if and only X is of class D. Solution 1. If If direction:
More informationExponentiated Gradient Descent
CSE599s, Spring 01, Online Learning Lecture 10-04/6/01 Lecturer: Ofer Dekel Exponentiated Gradient Descent Scribe: Albert Yu 1 Introduction In this lecture we review norms, dual norms, strong convexity,
More informationFunctional Analysis. Franck Sueur Metric spaces Definitions Completeness Compactness Separability...
Functional Analysis Franck Sueur 2018-2019 Contents 1 Metric spaces 1 1.1 Definitions........................................ 1 1.2 Completeness...................................... 3 1.3 Compactness......................................
More informationsample lectures: Compressed Sensing, Random Sampling I & II
P. Jung, CommIT, TU-Berlin]: sample lectures Compressed Sensing / Random Sampling I & II 1/68 sample lectures: Compressed Sensing, Random Sampling I & II Peter Jung Communications and Information Theory
More informationAn exponential family of distributions is a parametric statistical model having densities with respect to some positive measure λ of the form.
Stat 8112 Lecture Notes Asymptotics of Exponential Families Charles J. Geyer January 23, 2013 1 Exponential Families An exponential family of distributions is a parametric statistical model having densities
More informationDISCRETE MINIMAL ENERGY PROBLEMS
DISCRETE MINIMAL ENERGY PROBLEMS Lecture III E. B. Saff Center for Constructive Approximation Vanderbilt University University of Crete, Heraklion May, 2017 Random configurations ΩN = {X1, X2,..., XN }:
More informationOptimal Estimation of a Nonsmooth Functional
Optimal Estimation of a Nonsmooth Functional T. Tony Cai Department of Statistics The Wharton School University of Pennsylvania http://stat.wharton.upenn.edu/ tcai Joint work with Mark Low 1 Question Suppose
More informationExample 9 Algebraic Evaluation for Example 1
A Basic Principle Consider the it f(x) x a If you have a formula for the function f and direct substitution gives the indeterminate form 0, you may be able to evaluate the it algebraically. 0 Principle
More informationLecture 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 informationScaling limit of random planar maps Lecture 2.
Scaling limit of random planar maps Lecture 2. Olivier Bernardi, CNRS, Université Paris-Sud Workshop on randomness and enumeration Temuco, Olivier Bernardi p.1/25 Goal We consider quadrangulations as metric
More informationDefinition 6.1. A metric space (X, d) is complete if every Cauchy sequence tends to a limit in X.
Chapter 6 Completeness Lecture 18 Recall from Definition 2.22 that a Cauchy sequence in (X, d) is a sequence whose terms get closer and closer together, without any limit being specified. In the Euclidean
More informationOptimization and Optimal Control in Banach Spaces
Optimization and Optimal Control in Banach Spaces Bernhard Schmitzer October 19, 2017 1 Convex non-smooth optimization with proximal operators Remark 1.1 (Motivation). Convex optimization: easier to solve,
More informationLecture 12 Unconstrained Optimization (contd.) Constrained Optimization. October 15, 2008
Lecture 12 Unconstrained Optimization (contd.) Constrained Optimization October 15, 2008 Outline Lecture 11 Gradient descent algorithm Improvement to result in Lec 11 At what rate will it converge? Constrained
More informationMetric Spaces and Topology
Chapter 2 Metric Spaces and Topology From an engineering perspective, the most important way to construct a topology on a set is to define the topology in terms of a metric on the set. This approach underlies
More informationSMSTC (2017/18) Geometry and Topology 2.
SMSTC (2017/18) Geometry and Topology 2 Lecture 1: Differentiable Functions and Manifolds in R n Lecturer: Diletta Martinelli (Notes by Bernd Schroers) a wwwsmstcacuk 11 General remarks In this lecture
More informationSmall ball probabilities and metric entropy
Small ball probabilities and metric entropy Frank Aurzada, TU Berlin Sydney, February 2012 MCQMC Outline 1 Small ball probabilities vs. metric entropy 2 Connection to other questions 3 Recent results for
More informationMath 328 Course Notes
Math 328 Course Notes Ian Robertson March 3, 2006 3 Properties of C[0, 1]: Sup-norm and Completeness In this chapter we are going to examine the vector space of all continuous functions defined on the
More informationOn Stochastic Decompositions of Metric Spaces
On Stochastic Decompositions of Metric Spaces Scribe of a talk given at the fall school Metric Embeddings : Constructions and Obstructions. 3-7 November 204, Paris, France Ofer Neiman Abstract In this
More informationU e = E (U\E) e E e + U\E e. (1.6)
12 1 Lebesgue Measure 1.2 Lebesgue Measure In Section 1.1 we defined the exterior Lebesgue measure of every subset of R d. Unfortunately, a major disadvantage of exterior measure is that it does not satisfy
More informationThe Behavior of Algorithms in Practice 4/18/02 and 4/23/02. Lecture 15/16
18.9 The Behavior of Algorithms in Practice /18/2 and /23/2 Lecture 15/16 Lecturer: Dan Spielman Scribe: Mikhail Alekhnovitch Let a 1,..., a n be independent random gaussian points in the plane with variance
More informationAnother Riesz Representation Theorem
Another Riesz Representation Theorem In these notes we prove (one version of) a theorem known as the Riesz Representation Theorem. Some people also call it the Riesz Markov Theorem. It expresses positive
More informationLipschitz p-convex and q-concave maps
Lipschitz p-convex and q-concave maps J. Alejandro Chávez-Domínguez Instituto de Ciencias Matemáticas, CSIC-UAM-UCM-UC3M, Madrid and Department of Mathematics, University of Texas at Austin Conference
More informationBerge s Maximum Theorem
Berge s Maximum Theorem References: Acemoglu, Appendix A.6 Stokey-Lucas-Prescott, Section 3.3 Ok, Sections E.1-E.3 Claude Berge, Topological Spaces (1963), Chapter 6 Berge s Maximum Theorem So far, we
More informationUniversity of Pavia. M Estimators. Eduardo Rossi
University of Pavia M Estimators Eduardo Rossi Criterion Function A basic unifying notion is that most econometric estimators are defined as the minimizers of certain functions constructed from the sample
More informationIntroduction to Empirical Processes and Semiparametric Inference Lecture 08: Stochastic Convergence
Introduction to Empirical Processes and Semiparametric Inference Lecture 08: Stochastic Convergence Michael R. Kosorok, Ph.D. Professor and Chair of Biostatistics Professor of Statistics and Operations
More informationLecture 2. We now introduce some fundamental tools in martingale theory, which are useful in controlling the fluctuation of martingales.
Lecture 2 1 Martingales We now introduce some fundamental tools in martingale theory, which are useful in controlling the fluctuation of martingales. 1.1 Doob s inequality We have the following maximal
More informationBennett-type Generalization Bounds: Large-deviation Case and Faster Rate of Convergence
Bennett-type Generalization Bounds: Large-deviation Case and Faster Rate of Convergence Chao Zhang The Biodesign Institute Arizona State University Tempe, AZ 8587, USA Abstract In this paper, we present
More information14 : Theory of Variational Inference: Inner and Outer Approximation
10-708: Probabilistic Graphical Models 10-708, Spring 2017 14 : Theory of Variational Inference: Inner and Outer Approximation Lecturer: Eric P. Xing Scribes: Maria Ryskina, Yen-Chia Hsu 1 Introduction
More informationa) Let x,y be Cauchy sequences in some metric space. Define d(x, y) = lim n d (x n, y n ). Show that this function is well-defined.
Problem 3) Remark: for this problem, if I write the notation lim x n, it should always be assumed that I mean lim n x n, and similarly if I write the notation lim x nk it should always be assumed that
More informationCourse 212: Academic Year Section 1: Metric Spaces
Course 212: Academic Year 1991-2 Section 1: Metric Spaces D. R. Wilkins Contents 1 Metric Spaces 3 1.1 Distance Functions and Metric Spaces............. 3 1.2 Convergence and Continuity in Metric Spaces.........
More informationLebesgue Integration on R n
Lebesgue Integration on R n The treatment here is based loosely on that of Jones, Lebesgue Integration on Euclidean Space We give an overview from the perspective of a user of the theory Riemann integration
More information4th Preparation Sheet - Solutions
Prof. Dr. Rainer Dahlhaus Probability Theory Summer term 017 4th Preparation Sheet - Solutions Remark: Throughout the exercise sheet we use the two equivalent definitions of separability of a metric space
More information1 Dimension Reduction in Euclidean Space
CSIS0351/8601: Randomized Algorithms Lecture 6: Johnson-Lindenstrauss Lemma: Dimension Reduction Lecturer: Hubert Chan Date: 10 Oct 011 hese lecture notes are supplementary materials for the lectures.
More informationSome Background Math Notes on Limsups, Sets, and Convexity
EE599 STOCHASTIC NETWORK OPTIMIZATION, MICHAEL J. NEELY, FALL 2008 1 Some Background Math Notes on Limsups, Sets, and Convexity I. LIMITS Let f(t) be a real valued function of time. Suppose f(t) converges
More informationConvergence of latent mixing measures in nonparametric and mixture models 1
Convergence of latent mixing measures in nonparametric and mixture models 1 XuanLong Nguyen xuanlong@umich.edu Department of Statistics University of Michigan Technical Report 527 (Revised, Jan 25, 2012)
More informationON THE REGULARITY OF SAMPLE PATHS OF SUB-ELLIPTIC DIFFUSIONS ON MANIFOLDS
Bendikov, A. and Saloff-Coste, L. Osaka J. Math. 4 (5), 677 7 ON THE REGULARITY OF SAMPLE PATHS OF SUB-ELLIPTIC DIFFUSIONS ON MANIFOLDS ALEXANDER BENDIKOV and LAURENT SALOFF-COSTE (Received March 4, 4)
More information