Lecture 9: October 25, Lower bounds for minimax rates via multiple hypotheses
|
|
- Aubrey Paul
- 5 years ago
- Views:
Transcription
1 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 lecture to develop lower bounds using lower bounds for testing multiple hypotheses Recall that for a random variable V uniformly distrbuted over a set of hypotheses V, the probability of of error for any classifier T(x) with input x coming from P n v for a randomly chosen v V, is lower bounded as P [T(x) = V] n E v,v V [D(P v P v )] log V Recall that the above bound can be used to lower bound the minimax risk for a loss function l( θ, θ) = Φ d( θ, θ) and a set of distributions Π We proved in the last lecture that for a set of distributions P v } v V Π with the property that v = v, d(p v, P v ) δ, we have M n (Π, l) = inf θ sup P Π [ ] E l( θ(x), θ(p)) x P n Φ(δ) inf P [T(x) = V]} T To use the above bounds, we need to come up with a set of distributions which are far in terms of the property θ (so that the second bound is large), but close on aevrage in terms of KL-divergence (so that the first bound is large) This is also known as the local Fano method since we derived the first bound using Fano s inequality, and are applying it by using (a local bound on) KL-divergence for every pair of distributions P v, P v (recall that we used convexity of KL-divergence to reduce to the local setting) You can find other variants of this method in the notes by Duchi [Duc6] Gaussian mean estimation While binary hypothesis testing was used show a bound for estimating the mean of Bernoulli random variables, the multiple hypotheses setting is often useful in considering highdimensional problems We take Π to be the set of d-dimensional Gaussian distributions as below Π = N(µ, I d ) µ R d}
2 Let the property θ be the mean as before, and let l( θ, θ) = θ θ We first check the expected loss for the empirical mean estimator Proposition Let θ(x,, x n ) = n x i Then, for any µ R d, we have that E X (N(µ,I d )) n n X i µ = d n Proof: The proof is similar to the case of Bernoulli random variables By the (pairwise) independence of the n samples, we have that E X (N(µ,I d )) n n X i µ = [ ] n E X i µ + n E [ X i µ, X j µ ] i =j = n [ ] n E X µ X N(µ,I d ) = n n d = d n We will apply the local Fano method to prove the optimality of the above bound in terms of both d and n We first need the following expression for KL-divergenge of two normal distributions Exercise Prove (using the chain rule) that D(N(µ, I d ) N(µ, I d )) = ln µ µ Thus, we need to find a large collection of distributions, equivalent to finding a large collection of means, such that for any two µ = µ, we have that µ µ is somewhat large (to lower bound the loss), but still µ µ is small on average (to upper bound the average KL-divergence) It is actually quite easy for the setting above, but we will take a slightly longer route through covering and packing numbers to illustrate a general method Covering and packing numbers Definition 3 Let S be a set of points with a metric d(, ) A collection of points C S is called a δ-covering of S (with respect to the metric d) if x S, y C d(x, y) δ
3 A set of points P is called a δ-packing if x, y P, x = y d(x, y) δ The size of the minimal δ-covering, denoted as N(δ, S, d), is called the δ-covering number of S and the size of the maximal δ-packing is called the δ-packing number The quantity log N(δ, S, d) is also called the metric entropy of S We will take the required collection of means to be a scaled copy of a (/)-packing of the unit ball in R d (under the Euclidean distance) We will show a lower bound on the size of this collection (the packing number) by using a relatioship between the packing and covering numbers Exercise 4 For any set S, metric d and δ > 0, show that M(δ, S, d) N(δ, S, d) M(δ, S, d) (Hint: First prove that an optimal δ-packing must also be a δ-covering) Let B d (x, r) denote the ball in R d of radius r (in the Euclidean distance) with its center at x We know that Vol (B d (x, r)) = c d r d for some constant c d 0 Note that if C B d (0, ) is a δ-covering of B d (0, ), then B(0, ) x C B d (x, δ) Thus, we have c d = Vol (B d (0, )) Vol (B d (x, δ)) = N (δ, B d (0, ), ) c d δ d x C Combining with the previous relationship between covering and packing numbers, this gives M (δ, B d (0, ), ) N (δ, B d (0, ), ) δ d Thus, there exists a (/)-packing of B d (0, ) of size at least d We will use this to prove the lower bound for mean estimation 3 Back to lower bounds for mean estimation We can now get back to the lowe bound Let V be a (/)-packing of B d (0, ) of size at least d We consider the set of distributions N(4δ v, I d ) v V} 3
4 Since V is a (/)-packing, we have that for all P, P Π, θ(p) θ(p ) δ Also, since v v for any v, v V, we get that for any P, P Π, the means are at distance at most 8δ Hence, D(P P ) = ln µ µ ln (64δ ) = 3δ ln Applying the lower bound on minimax loss in terms of KL-divergences gives ( M n (Π, l) δ n ) ( (3δ / ln ) δ n ) (3δ / ln ) log V d 4 Sparse mean estimation From the previous examples, it seems like the empirical mean estimator is always the best one, and the role of information theory is primarily for proving lower bounds However, it can also serve as a guide for the right bound to aim for Consider the set of normal distributions, where the mean has only one non-zero coordinate } Π = N(µ, I d ) µ R d, µ 0 Let θ(p) = E x P [x] be the mean, and let l( θ, θ) = θ θ as before Exercise 5 Let V = e,, e d } be the set of standard basis vectors in R d Use the set of means µ v = v for v V to show that there exists a constant c such that M n (Π, l) c log d n The optimal estimator for the above problem actually extends the definition of the mean as the minimizer of the total square distance (from the sample points) For a sample X (R d ) n and j [d], we define µ (j) as a vector which is equal to the empirical mean in the j th coordinate and zero elsewhere ie, We take the estimator to be µ (j) k = n (X i ) j if k = j 0 otherwise µ = arg min µ 0, µ (),, µ (d) } } n X i µ This estimator indeed achieves an expected loss of O((log d)/n), but we will not discuss the proof here 4
5 References [Duc6] John Duchi Lecture notes on Information Theory and Statistics, 06 URL: 5
Lecture 21: Minimax Theory
Lecture : Minimax Theory Akshay Krishnamurthy akshay@cs.umass.edu November 8, 07 Recap In the first part of the course, we spent the majority of our time studying risk minimization. We found many ways
More information10-704: Information Processing and Learning Fall Lecture 21: Nov 14. sup
0-704: Information Processing and Learning Fall 206 Lecturer: Aarti Singh Lecture 2: Nov 4 Note: hese notes are based on scribed notes from Spring5 offering of this course LaeX template courtesy of UC
More informationECE598: Information-theoretic methods in high-dimensional statistics Spring 2016
ECE598: Information-theoretic methods in high-dimensional statistics Spring 06 Lecture : Mutual Information Method Lecturer: Yihong Wu Scribe: Jaeho Lee, Mar, 06 Ed. Mar 9 Quick review: Assouad s lemma
More informationLecture 17: Density Estimation Lecturer: Yihong Wu Scribe: Jiaqi Mu, Mar 31, 2016 [Ed. Apr 1]
ECE598: Information-theoretic methods in high-dimensional statistics Spring 06 Lecture 7: Density Estimation Lecturer: Yihong Wu Scribe: Jiaqi Mu, Mar 3, 06 [Ed. Apr ] In last lecture, we studied the minimax
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 information16.1 Bounding Capacity with Covering Number
ECE598: Information-theoretic methods in high-dimensional statistics Spring 206 Lecture 6: Upper Bounds for Density Estimation Lecturer: Yihong Wu Scribe: Yang Zhang, Apr, 206 So far we have been mostly
More information21.2 Example 1 : Non-parametric regression in Mean Integrated Square Error Density Estimation (L 2 2 risk)
10-704: Information Processing and Learning Spring 2015 Lecture 21: Examples of Lower Bounds and Assouad s Method Lecturer: Akshay Krishnamurthy Scribes: Soumya Batra Note: LaTeX template courtesy of UC
More informationLecture 10: October 30, 2017
Information an Coing Theory Autumn 2017 Lecturer: Mahur Tulsiani Lecture 10: October 30, 2017 1 I-Projections an applications In this lecture, we will talk more about fining the istribution in a set Π
More informationHands-On Learning Theory Fall 2016, Lecture 3
Hands-On Learning Theory Fall 016, Lecture 3 Jean Honorio jhonorio@purdue.edu 1 Information Theory First, we provide some information theory background. Definition 3.1 (Entropy). The entropy of a discrete
More informationMGMT 69000: Topics in High-dimensional Data Analysis Falll 2016
MGMT 69000: Topics in High-dimensional Data Analysis Falll 2016 Lecture 14: Information Theoretic Methods Lecturer: Jiaming Xu Scribe: Hilda Ibriga, Adarsh Barik, December 02, 2016 Outline f-divergence
More informationRobustness and duality of maximum entropy and exponential family distributions
Chapter 7 Robustness and duality of maximum entropy and exponential family distributions In this lecture, we continue our study of exponential families, but now we investigate their properties in somewhat
More informationLecture 7 Introduction to Statistical Decision Theory
Lecture 7 Introduction to Statistical Decision Theory I-Hsiang Wang Department of Electrical Engineering National Taiwan University ihwang@ntu.edu.tw December 20, 2016 1 / 55 I-Hsiang Wang IT Lecture 7
More informationExercises from other sources REAL NUMBERS 2,...,
Exercises from other sources REAL NUMBERS 1. Find the supremum and infimum of the following sets: a) {1, b) c) 12, 13, 14, }, { 1 3, 4 9, 13 27, 40 } 81,, { 2, 2 + 2, 2 + 2 + } 2,..., d) {n N : n 2 < 10},
More informationHomework 3: Solutions
Homework 3: Solutions ECS 20 (Fall 2014) Patrice Koehl koehl@cs.ucdavis.edu October 16, 2014 Exercise 1 Show that this implication is a tautology, by using a table of truth: [(p q) (p r) (q r)] r. p q
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 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 informationQuiz 2 Date: Monday, November 21, 2016
10-704 Information Processing and Learning Fall 2016 Quiz 2 Date: Monday, November 21, 2016 Name: Andrew ID: Department: Guidelines: 1. PLEASE DO NOT TURN THIS PAGE UNTIL INSTRUCTED. 2. Write your name,
More information15.1 Upper bound via Sudakov minorization
ECE598: Information-theoretic methos in high-imensional statistics Spring 206 Lecture 5: Suakov, Maurey, an uality of metric entropy Lecturer: Yihong Wu Scribe: Aolin Xu, Mar 7, 206 [E. Mar 24] In this
More informationLecture 3 January 28
EECS 28B / STAT 24B: Advanced Topics in Statistical LearningSpring 2009 Lecture 3 January 28 Lecturer: Pradeep Ravikumar Scribe: Timothy J. Wheeler Note: These lecture notes are still rough, and have only
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 informationLecture 8: Information Theory and Statistics
Lecture 8: Information Theory and Statistics Part II: Hypothesis Testing and I-Hsiang Wang Department of Electrical Engineering National Taiwan University ihwang@ntu.edu.tw December 23, 2015 1 / 50 I-Hsiang
More informationActive Learning: Disagreement Coefficient
Advanced Course in Machine Learning Spring 2010 Active Learning: Disagreement Coefficient Handouts are jointly prepared by Shie Mannor and Shai Shalev-Shwartz In previous lectures we saw examples in which
More informationOn Bayes Risk Lower Bounds
Journal of Machine Learning Research 17 (2016) 1-58 Submitted 4/16; Revised 10/16; Published 12/16 On Bayes Risk Lower Bounds Xi Chen Stern School of Business New York University New York, NY 10012, USA
More informationMachine Learning Basics Lecture 7: Multiclass Classification. Princeton University COS 495 Instructor: Yingyu Liang
Machine Learning Basics Lecture 7: Multiclass Classification Princeton University COS 495 Instructor: Yingyu Liang Example: image classification indoor Indoor outdoor Example: image classification (multiclass)
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 informationChapter 2. Binary and M-ary Hypothesis Testing 2.1 Introduction (Levy 2.1)
Chapter 2. Binary and M-ary Hypothesis Testing 2.1 Introduction (Levy 2.1) Detection problems can usually be casted as binary or M-ary hypothesis testing problems. Applications: This chapter: Simple hypothesis
More informationMIT Spring 2016
MIT 18.655 Dr. Kempthorne Spring 2016 1 MIT 18.655 Outline 1 2 MIT 18.655 3 Decision Problem: Basic Components P = {P θ : θ Θ} : parametric model. Θ = {θ}: Parameter space. A{a} : Action space. L(θ, a)
More informationMinimax Estimation of Kernel Mean Embeddings
Minimax Estimation of Kernel Mean Embeddings Bharath K. Sriperumbudur Department of Statistics Pennsylvania State University Gatsby Computational Neuroscience Unit May 4, 2016 Collaborators Dr. Ilya Tolstikhin
More informationOXPORD UNIVERSITY PRESS
Concentration Inequalities A Nonasymptotic Theory of Independence STEPHANE BOUCHERON GABOR LUGOSI PASCAL MASS ART OXPORD UNIVERSITY PRESS CONTENTS 1 Introduction 1 1.1 Sums of Independent Random Variables
More information40.530: Statistics. Professor Chen Zehua. Singapore University of Design and Technology
Singapore University of Design and Technology Lecture 9: Hypothesis testing, uniformly most powerful tests. The Neyman-Pearson framework Let P be the family of distributions of concern. The Neyman-Pearson
More informationLecture 8: Minimax Lower Bounds: LeCam, Fano, and Assouad
40.850: athematical Foundation of Big Data Analysis Spring 206 Lecture 8: inimax Lower Bounds: LeCam, Fano, and Assouad Lecturer: Fang Han arch 07 Disclaimer: These notes have not been subjected to the
More informationMinimax lower bounds I
Minimax lower bounds I Kyoung Hee Kim Sungshin University 1 Preliminaries 2 General strategy 3 Le Cam, 1973 4 Assouad, 1983 5 Appendix Setting Family of probability measures {P θ : θ Θ} on a sigma field
More informationHoeffding, Chernoff, Bennet, and Bernstein Bounds
Stat 928: Statistical Learning Theory Lecture: 6 Hoeffding, Chernoff, Bennet, Bernstein Bounds Instructor: Sham Kakade 1 Hoeffding s Bound We say X is a sub-gaussian rom variable if it has quadratically
More informationCharacterisation of Accumulation Points. Convergence in Metric Spaces. Characterisation of Closed Sets. Characterisation of Closed Sets
Convergence in Metric Spaces Functional Analysis Lecture 3: Convergence and Continuity in Metric Spaces Bengt Ove Turesson September 4, 2016 Suppose that (X, d) is a metric space. A sequence (x n ) X is
More informationHow hard is this function to optimize?
How hard is this function to optimize? John Duchi Based on joint work with Sabyasachi Chatterjee, John Lafferty, Yuancheng Zhu Stanford University West Coast Optimization Rumble October 2016 Problem minimize
More informationBEST TESTS. Abstract. We will discuss the Neymann-Pearson theorem and certain best test where the power function is optimized.
BEST TESTS Abstract. We will discuss the Neymann-Pearson theorem and certain best test where the power function is optimized. 1. Most powerful test Let {f θ } θ Θ be a family of pdfs. We will consider
More informationU Logo Use Guidelines
Information Theory Lecture 3: Applications to Machine Learning U Logo Use Guidelines Mark Reid logo is a contemporary n of our heritage. presents our name, d and our motto: arn the nature of things. authenticity
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 informationComputational and Statistical Learning theory
Computational and Statistical Learning theory Problem set 2 Due: January 31st Email solutions to : karthik at ttic dot edu Notation : Input space : X Label space : Y = {±1} Sample : (x 1, y 1,..., (x n,
More informationNotes on Decision Theory and Prediction
Notes on Decision Theory and Prediction Ronald Christensen Professor of Statistics Department of Mathematics and Statistics University of New Mexico October 7, 2014 1. Decision Theory Decision theory is
More informationSolutions to Assignment-11
Solutions to Assignment-. (a) For any sequence { } of positive numbers, show that lim inf + lim inf an lim sup an lim sup +. Show from this, that the root test is stronger than the ratio test. That is,
More informationLecture 1: Entropy, convexity, and matrix scaling CSE 599S: Entropy optimality, Winter 2016 Instructor: James R. Lee Last updated: January 24, 2016
Lecture 1: Entropy, convexity, and matrix scaling CSE 599S: Entropy optimality, Winter 2016 Instructor: James R. Lee Last updated: January 24, 2016 1 Entropy Since this course is about entropy maximization,
More informationThe proximal mapping
The proximal mapping http://bicmr.pku.edu.cn/~wenzw/opt-2016-fall.html Acknowledgement: this slides is based on Prof. Lieven Vandenberghes lecture notes Outline 2/37 1 closed function 2 Conjugate function
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 information1.1 Basis of Statistical Decision Theory
ECE598: Information-theoretic methods in high-dimensional statistics Spring 2016 Lecture 1: Introduction Lecturer: Yihong Wu Scribe: AmirEmad Ghassami, Jan 21, 2016 [Ed. Jan 31] Outline: Introduction of
More informationMathematics for Economists
Mathematics for Economists Victor Filipe Sao Paulo School of Economics FGV Metric Spaces: Basic Definitions Victor Filipe (EESP/FGV) Mathematics for Economists Jan.-Feb. 2017 1 / 34 Definitions and Examples
More informationMid Term-1 : Practice problems
Mid Term-1 : Practice problems These problems are meant only to provide practice; they do not necessarily reflect the difficulty level of the problems in the exam. The actual exam problems are likely to
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 informationLecture 13: p-values and union intersection tests
Lecture 13: p-values and union intersection tests p-values After a hypothesis test is done, one method of reporting the result is to report the size α of the test used to reject H 0 or accept H 0. If α
More informationMetric Spaces Math 413 Honors Project
Metric Spaces Math 413 Honors Project 1 Metric Spaces Definition 1.1 Let X be a set. A metric on X is a function d : X X R such that for all x, y, z X: i) d(x, y) = d(y, x); ii) d(x, y) = 0 if and only
More informationConstrained Optimization and Lagrangian Duality
CIS 520: Machine Learning Oct 02, 2017 Constrained Optimization and Lagrangian Duality Lecturer: Shivani Agarwal Disclaimer: These notes are designed to be a supplement to the lecture. They may or may
More information19.1 Maximum Likelihood estimator and risk upper bound
ECE598: Information-theoretic methods in high-dimensional statistics Spring 016 Lecture 19: Denoising sparse vectors - Ris upper bound Lecturer: Yihong Wu Scribe: Ravi Kiran Raman, Apr 1, 016 This lecture
More informationInformation-Theoretic Methods in Data Science
Information-Theoretic Methods in Data Science Information-theoretic bounds on sketching Mert Pilanci Department of Electrical Engineering Stanford University Contents Information-theoretic bounds on sketching
More informationA talk on Oracle inequalities and regularization. by Sara van de Geer
A talk on Oracle inequalities and regularization by Sara van de Geer Workshop Regularization in Statistics Banff International Regularization Station September 6-11, 2003 Aim: to compare l 1 and other
More informationEconomics 520. Lecture Note 19: Hypothesis Testing via the Neyman-Pearson Lemma CB 8.1,
Economics 520 Lecture Note 9: Hypothesis Testing via the Neyman-Pearson Lemma CB 8., 8.3.-8.3.3 Uniformly Most Powerful Tests and the Neyman-Pearson Lemma Let s return to the hypothesis testing problem
More informationIntroduction to Functional Analysis
Introduction to Functional Analysis Carnegie Mellon University, 21-640, Spring 2014 Acknowledgements These notes are based on the lecture course given by Irene Fonseca but may differ from the exact lecture
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 informationLecture 5: Likelihood ratio tests, Neyman-Pearson detectors, ROC curves, and sufficient statistics. 1 Executive summary
ECE 830 Spring 207 Instructor: R. Willett Lecture 5: Likelihood ratio tests, Neyman-Pearson detectors, ROC curves, and sufficient statistics Executive summary In the last lecture we saw that the likelihood
More informationMetric Spaces Lecture 17
Metric Spaces Lecture 17 Homeomorphisms At the end of last lecture an example was given of a bijective continuous function f such that f 1 is not continuous. For another example, consider the sets T =
More informationSome theoretical properties of GANs. Gérard Biau Toulouse, September 2018
Some theoretical properties of GANs Gérard Biau Toulouse, September 2018 Coauthors Benoît Cadre (ENS Rennes) Maxime Sangnier (Sorbonne University) Ugo Tanielian (Sorbonne University & Criteo) 1 video Source:
More informationGeneralization bounds
Advanced Course in Machine Learning pring 200 Generalization bounds Handouts are jointly prepared by hie Mannor and hai halev-hwartz he problem of characterizing learnability is the most basic question
More informationOn the interior of the simplex, we have the Hessian of d(x), Hd(x) is diagonal with ith. µd(w) + w T c. minimize. subject to w T 1 = 1,
Math 30 Winter 05 Solution to Homework 3. Recognizing the convexity of g(x) := x log x, from Jensen s inequality we get d(x) n x + + x n n log x + + x n n where the equality is attained only at x = (/n,...,
More information6.1 Variational representation of f-divergences
ECE598: Information-theoretic methods in high-dimensional statistics Spring 2016 Lecture 6: Variational representation, HCR and CR lower bounds Lecturer: Yihong Wu Scribe: Georgios Rovatsos, Feb 11, 2016
More informationApproximation Theoretical Questions for SVMs
Ingo Steinwart LA-UR 07-7056 October 20, 2007 Statistical Learning Theory: an Overview Support Vector Machines Informal Description of the Learning Goal X space of input samples Y space of labels, usually
More informationg 2 (x) (1/3)M 1 = (1/3)(2/3)M.
COMPACTNESS If C R n is closed and bounded, then by B-W it is sequentially compact: any sequence of points in C has a subsequence converging to a point in C Conversely, any sequentially compact C R n is
More informationMinimax risk bounds for linear threshold functions
CS281B/Stat241B (Spring 2008) Statistical Learning Theory Lecture: 3 Minimax risk bounds for linear threshold functions Lecturer: Peter Bartlett Scribe: Hao Zhang 1 Review We assume that there is a probability
More informationLearning with Rejection
Learning with Rejection Corinna Cortes 1, Giulia DeSalvo 2, and Mehryar Mohri 2,1 1 Google Research, 111 8th Avenue, New York, NY 2 Courant Institute of Mathematical Sciences, 251 Mercer Street, New York,
More informationTHE LASSO, CORRELATED DESIGN, AND IMPROVED ORACLE INEQUALITIES. By Sara van de Geer and Johannes Lederer. ETH Zürich
Submitted to the Annals of Applied Statistics arxiv: math.pr/0000000 THE LASSO, CORRELATED DESIGN, AND IMPROVED ORACLE INEQUALITIES By Sara van de Geer and Johannes Lederer ETH Zürich We study high-dimensional
More informationUniform concentration inequalities, martingales, Rademacher complexity and symmetrization
Uniform concentration inequalities, martingales, Rademacher complexity and symmetrization John Duchi Outline I Motivation 1 Uniform laws of large numbers 2 Loss minimization and data dependence II Uniform
More informationMachine Learning 4771
Machine Learning 477 Instructor: Tony Jebara Topic 5 Generalization Guarantees VC-Dimension Nearest Neighbor Classification (infinite VC dimension) Structural Risk Minimization Support Vector Machines
More information10-704: Information Processing and Learning Fall Lecture 24: Dec 7
0-704: Information Processing and Learning Fall 206 Lecturer: Aarti Singh Lecture 24: Dec 7 Note: These notes are based on scribed notes from Spring5 offering of this course. LaTeX template courtesy of
More informationLecture 2: August 31
0-704: Information Processing and Learning Fall 206 Lecturer: Aarti Singh Lecture 2: August 3 Note: These notes are based on scribed notes from Spring5 offering of this course. LaTeX template courtesy
More informationLecture 3: More on regularization. Bayesian vs maximum likelihood learning
Lecture 3: More on regularization. Bayesian vs maximum likelihood learning L2 and L1 regularization for linear estimators A Bayesian interpretation of regularization Bayesian vs maximum likelihood fitting
More informationContinuity. Matt Rosenzweig
Continuity Matt Rosenzweig Contents 1 Continuity 1 1.1 Rudin Chapter 4 Exercises........................................ 1 1.1.1 Exercise 1............................................. 1 1.1.2 Exercise
More information2 2 + x =
Lecture 30: Power series A Power Series is a series of the form c n = c 0 + c 1 x + c x + c 3 x 3 +... where x is a variable, the c n s are constants called the coefficients of the series. n = 1 + x +
More informationChapter 6. Hypothesis Tests Lecture 20: UMP tests and Neyman-Pearson lemma
Chapter 6. Hypothesis Tests Lecture 20: UMP tests and Neyman-Pearson lemma Theory of testing hypotheses X: a sample from a population P in P, a family of populations. Based on the observed X, we test a
More informationCombinatorics in Banach space theory Lecture 12
Combinatorics in Banach space theory Lecture The next lemma considerably strengthens the assertion of Lemma.6(b). Lemma.9. For every Banach space X and any n N, either all the numbers n b n (X), c n (X)
More informationOn the Complexity of Best Arm Identification with Fixed Confidence
On the Complexity of Best Arm Identification with Fixed Confidence Discrete Optimization with Noise Aurélien Garivier, Emilie Kaufmann COLT, June 23 th 2016, New York Institut de Mathématiques de Toulouse
More information2 Sequences, Continuity, and Limits
2 Sequences, Continuity, and Limits In this chapter, we introduce the fundamental notions of continuity and limit of a real-valued function of two variables. As in ACICARA, the definitions as well as proofs
More information16.4. Power Series. Introduction. Prerequisites. Learning Outcomes
Power Series 6.4 Introduction In this Section we consider power series. These are examples of infinite series where each term contains a variable, x, raised to a positive integer power. We use the ratio
More informationLecture 8 Plus properties, merit functions and gap functions. September 28, 2008
Lecture 8 Plus properties, merit functions and gap functions September 28, 2008 Outline Plus-properties and F-uniqueness Equation reformulations of VI/CPs Merit functions Gap merit functions FP-I book:
More informationQuasi-conformal maps and Beltrami equation
Chapter 7 Quasi-conformal maps and Beltrami equation 7. Linear distortion Assume that f(x + iy) =u(x + iy)+iv(x + iy) be a (real) linear map from C C that is orientation preserving. Let z = x + iy and
More informationStatistics & Data Sciences: First Year Prelim Exam May 2018
Statistics & Data Sciences: First Year Prelim Exam May 2018 Instructions: 1. Do not turn this page until instructed to do so. 2. Start each new question on a new sheet of paper. 3. This is a closed book
More informationLecture 23: UMPU tests in exponential families
Lecture 23: UMPU tests in exponential families Continuity of the power function For a given test T, the power function β T (P) is said to be continuous in θ if and only if for any {θ j : j = 0,1,2,...}
More informationCS 573: Algorithmic Game Theory Lecture date: January 23rd, 2008
CS 573: Algorithmic Game Theory Lecture date: January 23rd, 2008 Instructor: Chandra Chekuri Scribe: Bolin Ding Contents 1 2-Player Zero-Sum Game 1 1.1 Min-Max Theorem for 2-Player Zero-Sum Game....................
More informationRandomized algorithm
Tutorial 4 Joyce 2009-11-24 Outline Solution to Midterm Question 1 Question 2 Question 1 Question 2 Question 3 Question 4 Question 5 Solution to Midterm Solution to Midterm Solution to Midterm Question
More information25 Minimum bandwidth: Approximation via volume respecting embeddings
25 Minimum bandwidth: Approximation via volume respecting embeddings We continue the study of Volume respecting embeddings. In the last lecture, we motivated the use of volume respecting embeddings by
More informationEE/Stats 376A: Homework 7 Solutions Due on Friday March 17, 5 pm
EE/Stats 376A: Homework 7 Solutions Due on Friday March 17, 5 pm 1. Feedback does not increase the capacity. Consider a channel with feedback. We assume that all the recieved outputs are sent back immediately
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 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 informationThe Caratheodory Construction of Measures
Chapter 5 The Caratheodory Construction of Measures Recall how our construction of Lebesgue measure in Chapter 2 proceeded from an initial notion of the size of a very restricted class of subsets of R,
More informationHomework 1 Due: Wednesday, September 28, 2016
0-704 Information Processing and Learning Fall 06 Homework Due: Wednesday, September 8, 06 Notes: For positive integers k, [k] := {,..., k} denotes te set of te first k positive integers. Wen p and Y q
More informationMcGill University Math 354: Honors Analysis 3
Practice problems McGill University Math 354: Honors Analysis 3 not for credit Problem 1. Determine whether the family of F = {f n } functions f n (x) = x n is uniformly equicontinuous. 1st Solution: The
More informationFunctions of Several Variables
Jim Lambers MAT 419/519 Summer Session 2011-12 Lecture 2 Notes These notes correspond to Section 1.2 in the text. Functions of Several Variables We now generalize the results from the previous section,
More informationTHE INVERSE FUNCTION THEOREM FOR LIPSCHITZ MAPS
THE INVERSE FUNCTION THEOREM FOR LIPSCHITZ MAPS RALPH HOWARD DEPARTMENT OF MATHEMATICS UNIVERSITY OF SOUTH CAROLINA COLUMBIA, S.C. 29208, USA HOWARD@MATH.SC.EDU Abstract. This is an edited version of a
More informationCS Lecture 19. Exponential Families & Expectation Propagation
CS 6347 Lecture 19 Exponential Families & Expectation Propagation Discrete State Spaces We have been focusing on the case of MRFs over discrete state spaces Probability distributions over discrete spaces
More informationExercises with solutions (Set D)
Exercises with solutions Set D. A fair die is rolled at the same time as a fair coin is tossed. Let A be the number on the upper surface of the die and let B describe the outcome of the coin toss, where
More informationMath 5052 Measure Theory and Functional Analysis II Homework Assignment 7
Math 5052 Measure Theory and Functional Analysis II Homework Assignment 7 Prof. Wickerhauser Due Friday, February 5th, 2016 Please do Exercises 3, 6, 14, 16*, 17, 18, 21*, 23*, 24, 27*. Exercises marked
More informationSample width for multi-category classifiers
R u t c o r Research R e p o r t Sample width for multi-category classifiers Martin Anthony a Joel Ratsaby b RRR 29-2012, November 2012 RUTCOR Rutgers Center for Operations Research Rutgers University
More informationSTAT 200C: High-dimensional Statistics
STAT 200C: High-dimensional Statistics Arash A. Amini May 30, 2018 1 / 57 Table of Contents 1 Sparse linear models Basis Pursuit and restricted null space property Sufficient conditions for RNS 2 / 57
More information