Minimax Rates. Homology Inference

Size: px
Start display at page:

Download "Minimax Rates. Homology Inference"

Transcription

1 Minimax Rates for Homology Inference Don Sheehy Joint work with Sivaraman Balakrishan, Alessandro Rinaldo, Aarti Singh, and Larry Wasserman

2 Something like a joke.

3 Something like a joke. What is topological inference?

4 Something like a joke. What is topological inference? It s when you infer the topology of a space given only a finite subset.

5 Something like a joke. What is topological inference? It s when you infer the topology of a space given only a finite subset.

6 We add geometric and statistical hypotheses to make the problem well-posed. Geometric Assumption: The underlying space is a smooth manifold M. Statistical Assumption: The points are drawn i.i.d. from a distribution derived from M.

7 We add geometric and statistical hypotheses to make the problem well-posed. Geometric Assumption: The underlying space is a smooth manifold M. Statistical Assumption: The points are drawn i.i.d. from a distribution derived from M.

8 We add geometric and statistical hypotheses to make the problem well-posed. Geometric Assumption: The underlying space is a smooth manifold M. Statistical Assumption: The points are drawn i.i.d. from a distribution derived from M.

9 We add geometric and statistical hypotheses to make the problem well-posed. Geometric Assumption: The underlying space is a smooth manifold M. Statistical Assumption: The points are drawn i.i.d. from a distribution derived from M.

10

11 Input: n points from a d-manifold M in D-dimensions.

12 Input: n points from a d-manifold M in D-dimensions. Output: The homology of M.

13 Input: n points from a d-manifold M in D-dimensions. Output: The homology of M. Upper bound: What is the worst case complexity?

14 Input: n points from a d-manifold M in D-dimensions. Output: The homology of M. Upper bound: What is the worst case complexity? Lower Bound: What is the worst case complexity of the best possible algorithm?

15 sampled i.i.d. Input: n points from a d-manifold M in D-dimensions. Output: The homology of M. Upper bound: What is the worst case complexity? Lower Bound: What is the worst case complexity of the best possible algorithm?

16 sampled i.i.d. distribution supported on Input: n points from a d-manifold M in D-dimensions. Output: The homology of M. Upper bound: What is the worst case complexity? Lower Bound: What is the worst case complexity of the best possible algorithm?

17 sampled i.i.d. distribution supported on Input: n points from a d-manifold M in D-dimensions. with noise Output: The homology of M. Upper bound: What is the worst case complexity? Lower Bound: What is the worst case complexity of the best possible algorithm?

18 sampled i.i.d. distribution supported on Input: n points from a d-manifold M in D-dimensions. an estimate of with noise Output: The homology of M. Upper bound: What is the worst case complexity? Lower Bound: What is the worst case complexity of the best possible algorithm?

19 sampled i.i.d. distribution supported on Input: n points from a d-manifold M in D-dimensions. an estimate of with noise Output: The homology of M. Upper bound: What is the worst case complexity? Lower Bound: What is the worst case complexity of the best possible algorithm? probability of giving a wrong answer

20 sampled i.i.d. distribution supported on Input: n points from a d-manifold M in D-dimensions. an estimate of with noise Output: The homology of M. Upper bound: What is the worst case complexity? Lower Bound: What is the worst case complexity of the best possible algorithm? probability of giving a wrong answer The Goal: Matching Bounds (asymptotically)

21 Minimax risk is the error probability of the best estimator on the hardest examples.

22 Minimax risk is the error probability of the best estimator on the hardest examples. Minimax Risk: R n =inf Ĥ sup Q Q Q n (Ĥ H(M))

23 Minimax risk is the error probability of the best estimator on the hardest examples. Minimax Risk: R n =inf Ĥ sup Q Q Q n (Ĥ H(M)) the best estimator

24 Minimax risk is the error probability of the best estimator on the hardest examples. Minimax Risk: R n =inf Ĥ sup Q Q Q n (Ĥ H(M)) the best estimator the hardest distribution

25 Minimax risk is the error probability of the best estimator on the hardest examples. Minimax Risk: R n =inf Ĥ sup Q Q Q n (Ĥ H(M)) the best estimator the hardest distribution product distribution

26 Minimax risk is the error probability of the best estimator on the hardest examples. Minimax Risk: R n =inf Ĥ sup Q Q the best estimator the hardest distribution Q n (Ĥ H(M)) product distribution the true homology

27 Minimax risk is the error probability of the best estimator on the hardest examples. Minimax Risk: R n =inf Ĥ sup Q Q the best estimator the hardest distribution Q n (Ĥ H(M)) product distribution the true homology Sample Complexity: n(ɛ) =min{n : R n ɛ}

28 We assume manifolds without boundary of bounded volume and reach.

29 We assume manifolds without boundary of bounded volume and reach. Let M be the set of compact d-dimensional Riemannian manifolds without boundary such that

30 We assume manifolds without boundary of bounded volume and reach. Let M be the set of compact d-dimensional Riemannian manifolds without boundary such that 1 M ball D (0, 1)

31 We assume manifolds without boundary of bounded volume and reach. Let M be the set of compact d-dimensional Riemannian manifolds without boundary such that 1 M ball D (0, 1) 2 vol(m) c d

32 We assume manifolds without boundary of bounded volume and reach. Let M be the set of compact d-dimensional Riemannian manifolds without boundary such that 1 M ball D (0, 1) 2 3 vol(m) c d The reach of M is at most τ.

33 We assume manifolds without boundary of bounded volume and reach. Let M be the set of compact d-dimensional Riemannian manifolds without boundary such that 1 M ball D (0, 1) 2 3 vol(m) c d The reach of M is at most τ. Let P be the set of probability distributions supported over M Mwith densities bounded from below by a constant a.

34 We consider 4 different noise models. Noiseless Clutter Tubular Additive

35 We consider 4 different noise models. Noiseless Clutter Q = P Tubular Additive

36 We consider 4 different noise models. Noiseless Clutter Q = P Q =(1 γ)u + γp P P U is uniform on ball(0, 1) Tubular Additive

37 We consider 4 different noise models. Noiseless Clutter Q = P Q =(1 γ)u + γp P P U is uniform on ball(0, 1) Tubular Let Q M,σ be uniform on M σ. Additive Q = {Q M,σ : M M}

38 We consider 4 different noise models. Noiseless Clutter Q = P Q =(1 γ)u + γp P P U is uniform on ball(0, 1) Tubular Let Q M,σ be uniform on M σ. Q = {Q M,σ : M M} Additive Q = {P Φ:P P} Φ is Gaussian with σ τ or Φ has Fourier transform bounded away from 0 and τ is fixed.

39 Le Cam s Lemma is a powerful tool for proving minimax lower bounds.

40 Le Cam s Lemma is a powerful tool for proving minimax lower bounds. Lemma. Let Q be a set of distributions. Let θ(q) take values in a metric space (X, ρ) for Q Q. For any Q 1,Q 2 Q, inf ˆθ sup Q Q E Q n [ ] ρ(ˆθ, θ(q)) 1 8 ρ(θ(q 1),θ(Q 2 ))(1 TV(Q 1,Q 2 )) 2n

41 Le Cam s Lemma is a powerful tool for proving minimax lower bounds. Lemma. Let Q be a set of distributions. Let θ(q) take values in a metric space (X, ρ) for Q Q. For any Q 1,Q 2 Q, inf ˆθ sup Q Q E Q n [ ] ρ(ˆθ, θ(q)) 1 8 ρ(θ(q 1),θ(Q 2 ))(1 TV(Q 1,Q 2 )) 2n For homology, use the trivial metric. ρ(x, y) = { 0 if x = y 1 if x y

42 Le Cam s Lemma is a powerful tool for proving minimax lower bounds. Lemma. Let Q be a set of distributions. Let θ(q) take values in a metric space (X, ρ) for Q Q. For any Q 1,Q 2 Q, inf ˆθ sup Q Q E Q n [ ] ρ(ˆθ, θ(q)) 1 8 ρ(θ(q 1),θ(Q 2 ))(1 TV(Q 1,Q 2 )) 2n For homology, use the trivial metric. ρ(x, y) = { 0 if x = y 1 if x y inf Ĥ sup Q Q Q n (Ĥ H(M)) 1 8 (1 TV(Q 1,Q 2 )) 2n

43 Le Cam s Lemma is a powerful tool for proving minimax lower bounds. Lemma. Let Q be a set of distributions. Let θ(q) take values in a metric space (X, ρ) for Q Q. For any Q 1,Q 2 Q, inf ˆθ sup Q Q E Q n [ ] ρ(ˆθ, θ(q)) 1 8 ρ(θ(q 1),θ(Q 2 ))(1 TV(Q 1,Q 2 )) 2n For homology, use the trivial metric. ρ(x, y) = { 0 if x = y 1 if x y R n = inf Ĥ sup Q Q Q n (Ĥ H(M)) 1 8 (1 TV(Q 1,Q 2 )) 2n

44 The lower bound requires two manifolds that are geometrically close but topologically distinct.

45 The lower bound requires two manifolds that are geometrically close but topologically distinct. B =ball d (0, 1 τ) A = B \ ball d (0, 2τ)

46 The lower bound requires two manifolds that are geometrically close but topologically distinct. B =ball d (0, 1 τ) A = B \ ball d (0, 2τ) M 1 = (B τ ) M 2 = (A τ )

47 The lower bound requires two manifolds that are geometrically close but topologically distinct. B =ball d (0, 1 τ) A = B \ ball d (0, 2τ) M 1 = (B τ ) M 2 = (A τ ) The overlap

48 It suffices to bound the total variation distance.

49 It suffices to bound the total variation distance. Total Variation Distance: TV(Q 1,Q 2 )=sup A Q 1 (A) Q 2 (A) a max{vol(m 1 \ M 2 ), vol(m 2 \ M 1 )} C d aτ d

50 It suffices to bound the total variation distance. Total Variation Distance: Minimax Risk: TV(Q 1,Q 2 )=sup A Q 1 (A) Q 2 (A) a max{vol(m 1 \ M 2 ), vol(m 2 \ M 1 )} C d aτ d R n 1 8 (1 TV(Q 1,Q 2 ) 2n 1 8 (1 C daτ d ) 2n 1 8 e 2C daτ d n

51 It suffices to bound the total variation distance. Total Variation Distance: Minimax Risk: TV(Q 1,Q 2 )=sup A Q 1 (A) Q 2 (A) a max{vol(m 1 \ M 2 ), vol(m 2 \ M 1 )} C d aτ d R n 1 8 (1 TV(Q 1,Q 2 ) 2n 1 8 (1 C daτ d ) 2n 1 8 e 2C daτ d n Sampling Rate: n(ɛ) ( 1 τ ) d log 1 ε

52 The upper bound uses a union of balls to estimate the homology of M.

53 The upper bound uses a union of balls to estimate the homology of M.

54 The upper bound uses a union of balls to estimate the homology of M.

55 The upper bound uses a union of balls to estimate the homology of M. 1 Take a union of balls.

56 The upper bound uses a union of balls to estimate the homology of M. 1 Take a union of balls. Compute the homology of the 2 resulting Cech complex.

57 The upper bound uses a union of balls to estimate the homology of M. 1 Take a union of balls. Compute the homology of the 2 resulting Cech complex.

58 The upper bound uses a union of balls to estimate the homology of M. 0 1 Denoise the data. Take a union of balls. Compute the homology of the 2 resulting Cech complex.

59 The upper bound uses a union of balls to estimate the homology of M. 0 1 Denoise the data. Take a union of balls. Compute the homology of the 2 resulting Cech complex.

60 The upper bound uses a union of balls to estimate the homology of M. 0 1 Denoise the data. Take a union of balls. Compute the homology of the 2 resulting Cech complex.

61 The upper bound uses a union of balls to estimate the homology of M. 0 1 Denoise the data. Take a union of balls. Compute the homology of the 2 resulting Cech complex.

62 The upper bound uses a union of balls to estimate the homology of M. 0 1 Denoise the data. Take a union of balls. Compute the homology of the 2 resulting Cech complex.

63 The upper bound uses a union of balls to estimate the homology of M. 0 1 Denoise the data. Take a union of balls. Compute the homology of the 2 resulting Cech complex. To prove: The density is bounded from below near M and from above far from M.

64 Many fundamental problems are still open.

65 Many fundamental problems are still open. 1 Is the reach the right parameter?

66 Many fundamental problems are still open. 1 Is the reach the right parameter? 2 What about manifolds with boundary?

67 Many fundamental problems are still open. 1 Is the reach the right parameter? 2 What about manifolds with boundary? 3 Homotopy equivalence?

68 Many fundamental problems are still open. 1 Is the reach the right parameter? 2 What about manifolds with boundary? 3 Homotopy equivalence? 4 How to choose parameters?

69 Many fundamental problems are still open. 1 Is the reach the right parameter? 2 What about manifolds with boundary? 3 Homotopy equivalence? 4 How to choose parameters? 5 Are there efficient algorithms?

70 Thank you.

Minimax Rates for Homology Inference

Minimax Rates for Homology Inference Minimax Rates for Homology Inference Sivaraman Balakrishnan Alessandro Rinaldo Don Sheehy Aarti Singh Larry Wasserman Carnegie Mellon University INRIA Our upper bounds mainly generalize those in the work

More information

Minimax Estimation of Kernel Mean Embeddings

Minimax 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 information

Some Topics in Computational Topology

Some Topics in Computational Topology Some Topics in Computational Topology Yusu Wang Ohio State University AMS Short Course 2014 Introduction Much recent developments in computational topology Both in theory and in their applications E.g,

More information

Some Topics in Computational Topology. Yusu Wang. AMS Short Course 2014

Some Topics in Computational Topology. Yusu Wang. AMS Short Course 2014 Some Topics in Computational Topology Yusu Wang AMS Short Course 2014 Introduction Much recent developments in computational topology Both in theory and in their applications E.g, the theory of persistence

More information

Persistent homology and nonparametric regression

Persistent homology and nonparametric regression Cleveland State University March 10, 2009, BIRS: Data Analysis using Computational Topology and Geometric Statistics joint work with Gunnar Carlsson (Stanford), Moo Chung (Wisconsin Madison), Peter Kim

More information

Multivariate Topological Data Analysis

Multivariate Topological Data Analysis Cleveland State University November 20, 2008, Duke University joint work with Gunnar Carlsson (Stanford), Peter Kim and Zhiming Luo (Guelph), and Moo Chung (Wisconsin Madison) Framework Ideal Truth (Parameter)

More information

LECTURE 15: COMPLETENESS AND CONVEXITY

LECTURE 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 information

The Intersection of Statistics and Topology:

The Intersection of Statistics and Topology: The Intersection of Statistics and Topology: Confidence Sets for Persistence Diagrams Brittany Terese Fasy joint work with S. Balakrishnan, F. Lecci, A. Rinaldo, A. Singh, L. Wasserman 3 June 2014 [FLRWBS]

More information

Statistics and Topological Data Analysis

Statistics and Topological Data Analysis Geometry Understanding in Higher Dimensions CHAIRE D INFORMATIQUE ET SCIENCES NUMÉRIQUES Collège de France - June 2017 Statistics and Topological Data Analysis Bertrand MICHEL Ecole Centrale de Nantes

More information

Persistent Homology of Data, Groups, Function Spaces, and Landscapes.

Persistent Homology of Data, Groups, Function Spaces, and Landscapes. Persistent Homology of Data, Groups, Function Spaces, and Landscapes. Shmuel Weinberger Department of Mathematics University of Chicago William Benter Lecture City University of Hong Kong Liu Bie Ju Centre

More information

Metric Thickenings of Euclidean Submanifolds

Metric Thickenings of Euclidean Submanifolds Metric Thickenings of Euclidean Submanifolds Advisor: Dr. Henry Adams Committe: Dr. Chris Peterson, Dr. Daniel Cooley Joshua Mirth Masters Thesis Defense October 3, 2017 Introduction Motivation Can we

More information

The uniformization theorem

The uniformization theorem 1 The uniformization theorem Thurston s basic insight in all four of the theorems discussed in this book is that either the topology of the problem induces an appropriate geometry or there is an understandable

More information

Geometric Inference on Kernel Density Estimates

Geometric Inference on Kernel Density Estimates Geometric Inference on Kernel Density Estimates Bei Wang 1 Jeff M. Phillips 2 Yan Zheng 2 1 Scientific Computing and Imaging Institute, University of Utah 2 School of Computing, University of Utah Feb

More information

MAT 530: Topology&Geometry, I Fall 2005

MAT 530: Topology&Geometry, I Fall 2005 MAT 530: Topology&Geometry, I Fall 2005 Midterm Solutions Note: These solutions are more detailed than solutions sufficient for full credit. Let X denote the set {a, b, c}. The collections Problem 1 5+5

More information

Transversality. Abhishek Khetan. December 13, Basics 1. 2 The Transversality Theorem 1. 3 Transversality and Homotopy 2

Transversality. Abhishek Khetan. December 13, Basics 1. 2 The Transversality Theorem 1. 3 Transversality and Homotopy 2 Transversality Abhishek Khetan December 13, 2017 Contents 1 Basics 1 2 The Transversality Theorem 1 3 Transversality and Homotopy 2 4 Intersection Number Mod 2 4 5 Degree Mod 2 4 1 Basics Definition. Let

More information

Unique equilibrium states for geodesic flows in nonpositive curvature

Unique equilibrium states for geodesic flows in nonpositive curvature Unique equilibrium states for geodesic flows in nonpositive curvature Todd Fisher Department of Mathematics Brigham Young University Fractal Geometry, Hyperbolic Dynamics and Thermodynamical Formalism

More information

We will outline two proofs of the main theorem:

We will outline two proofs of the main theorem: Chapter 4 Higher Genus Surfaces 4.1 The Main Result We will outline two proofs of the main theorem: Theorem 4.1.1. Let Σ be a closed oriented surface of genus g > 1. Then every homotopy class of homeomorphisms

More information

Introduction 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 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 information

Lecture 7 Introduction to Statistical Decision Theory

Lecture 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 information

Distribution-Free Distribution Regression

Distribution-Free Distribution Regression Distribution-Free Distribution Regression Barnabás Póczos, Alessandro Rinaldo, Aarti Singh and Larry Wasserman AISTATS 2013 Presented by Esther Salazar Duke University February 28, 2014 E. Salazar (Reading

More information

19.1 Problem setup: Sparse linear regression

19.1 Problem setup: Sparse linear regression ECE598: Information-theoretic methods in high-dimensional statistics Spring 2016 Lecture 19: Minimax rates for sparse linear regression Lecturer: Yihong Wu Scribe: Subhadeep Paul, April 13/14, 2016 In

More information

Semi-Supervised Learning by Multi-Manifold Separation

Semi-Supervised Learning by Multi-Manifold Separation Semi-Supervised Learning by Multi-Manifold Separation Xiaojin (Jerry) Zhu Department of Computer Sciences University of Wisconsin Madison Joint work with Andrew Goldberg, Zhiting Xu, Aarti Singh, and Rob

More information

Geometric inference for measures based on distance functions The DTM-signature for a geometric comparison of metric-measure spaces from samples

Geometric inference for measures based on distance functions The DTM-signature for a geometric comparison of metric-measure spaces from samples Distance to Geometric inference for measures based on distance functions The - for a geometric comparison of metric-measure spaces from samples the Ohio State University wan.252@osu.edu 1/31 Geometric

More information

Gaussian Estimation under Attack Uncertainty

Gaussian Estimation under Attack Uncertainty Gaussian Estimation under Attack Uncertainty Tara Javidi Yonatan Kaspi Himanshu Tyagi Abstract We consider the estimation of a standard Gaussian random variable under an observation attack where an adversary

More information

10-704: Information Processing and Learning Fall Lecture 21: Nov 14. sup

10-704: 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 information

We have the following immediate corollary. 1

We have the following immediate corollary. 1 1. Thom Spaces and Transversality Definition 1.1. Let π : E B be a real k vector bundle with a Euclidean metric and let E 1 be the set of elements of norm 1. The Thom space T (E) of E is the quotient E/E

More information

QUALIFYING EXAMINATION Harvard University Department of Mathematics Tuesday 10 February 2004 (Day 1)

QUALIFYING EXAMINATION Harvard University Department of Mathematics Tuesday 10 February 2004 (Day 1) Tuesday 10 February 2004 (Day 1) 1a. Prove the following theorem of Banach and Saks: Theorem. Given in L 2 a sequence {f n } which weakly converges to 0, we can select a subsequence {f nk } such that the

More information

Problem Set 1: Solutions Math 201A: Fall Problem 1. Let (X, d) be a metric space. (a) Prove the reverse triangle inequality: for every x, y, z X

Problem Set 1: Solutions Math 201A: Fall Problem 1. Let (X, d) be a metric space. (a) Prove the reverse triangle inequality: for every x, y, z X Problem Set 1: s Math 201A: Fall 2016 Problem 1. Let (X, d) be a metric space. (a) Prove the reverse triangle inequality: for every x, y, z X d(x, y) d(x, z) d(z, y). (b) Prove that if x n x and y n y

More information

A Resampling Method on Pivotal Estimating Functions

A Resampling Method on Pivotal Estimating Functions A Resampling Method on Pivotal Estimating Functions Kun Nie Biostat 277,Winter 2004 March 17, 2004 Outline Introduction A General Resampling Method Examples - Quantile Regression -Rank Regression -Simulation

More information

Local Minimax Testing

Local Minimax Testing Local Minimax Testing Sivaraman Balakrishnan and Larry Wasserman Carnegie Mellon June 11, 2017 1 / 32 Hypothesis testing beyond classical regimes Example 1: Testing distribution of bacteria in gut microbiome

More information

Assignment #10 Morgan Schreffler 1 of 7

Assignment #10 Morgan Schreffler 1 of 7 Assignment #10 Morgan Schreffler 1 of 7 Lee, Chapter 4 Exercise 10 Let S be the square I I with the order topology generated by the dictionary topology. (a) Show that S has the least uppper bound property.

More information

Optimal Covariance Change Point Detection in High Dimension

Optimal Covariance Change Point Detection in High Dimension Optimal Covariance Change Point Detection in High Dimension Joint work with Daren Wang and Alessandro Rinaldo, CMU Yi Yu School of Mathematics, University of Bristol Outline Review of change point detection

More information

Math 4317 : Real Analysis I Mid-Term Exam 1 25 September 2012

Math 4317 : Real Analysis I Mid-Term Exam 1 25 September 2012 Instructions: Answer all of the problems. Math 4317 : Real Analysis I Mid-Term Exam 1 25 September 2012 Definitions (2 points each) 1. State the definition of a metric space. A metric space (X, d) is set

More information

Topological Simplification in 3-Dimensions

Topological Simplification in 3-Dimensions Topological Simplification in 3-Dimensions David Letscher Saint Louis University Computational & Algorithmic Topology Sydney Letscher (SLU) Topological Simplification CATS 2017 1 / 33 Motivation Original

More information

LECTURE 3: SMOOTH FUNCTIONS

LECTURE 3: SMOOTH FUNCTIONS LECTURE 3: SMOOTH FUNCTIONS Let M be a smooth manifold. 1. Smooth Functions Definition 1.1. We say a function f : M R is smooth if for any chart {ϕ α, U α, V α } in A that defines the smooth structure

More information

Convergence of Quantum Statistical Experiments

Convergence of Quantum Statistical Experiments Convergence of Quantum Statistical Experiments M!d!lin Gu"! University of Nottingham Jonas Kahn (Paris-Sud) Richard Gill (Leiden) Anna Jen#ová (Bratislava) Statistical experiments and statistical decision

More information

Testing Algebraic Hypotheses

Testing Algebraic Hypotheses Testing Algebraic Hypotheses Mathias Drton Department of Statistics University of Chicago 1 / 18 Example: Factor analysis Multivariate normal model based on conditional independence given hidden variable:

More information

EXPOSITORY NOTES ON DISTRIBUTION THEORY, FALL 2018

EXPOSITORY NOTES ON DISTRIBUTION THEORY, FALL 2018 EXPOSITORY NOTES ON DISTRIBUTION THEORY, FALL 2018 While these notes are under construction, I expect there will be many typos. The main reference for this is volume 1 of Hörmander, The analysis of liner

More information

Learning Theory. Ingo Steinwart University of Stuttgart. September 4, 2013

Learning Theory. Ingo Steinwart University of Stuttgart. September 4, 2013 Learning Theory Ingo Steinwart University of Stuttgart September 4, 2013 Ingo Steinwart University of Stuttgart () Learning Theory September 4, 2013 1 / 62 Basics Informal Introduction Informal Description

More information

1.4 The Jacobian of a map

1.4 The Jacobian of a map 1.4 The Jacobian of a map Derivative of a differentiable map Let F : M n N m be a differentiable map between two C 1 manifolds. Given a point p M we define the derivative of F at p by df p df (p) : T p

More information

Lecture 35: December The fundamental statistical distances

Lecture 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 information

Lecture Learning infinite hypothesis class via VC-dimension and Rademacher complexity;

Lecture 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 information

Weak convergence and Brownian Motion. (telegram style notes) P.J.C. Spreij

Weak convergence and Brownian Motion. (telegram style notes) P.J.C. Spreij Weak convergence and Brownian Motion (telegram style notes) P.J.C. Spreij this version: December 8, 2006 1 The space C[0, ) In this section we summarize some facts concerning the space C[0, ) of real

More information

A sampling theory for compact sets

A sampling theory for compact sets ENS Lyon January 2010 A sampling theory for compact sets F. Chazal Geometrica Group INRIA Saclay To download these slides: http://geometrica.saclay.inria.fr/team/fred.chazal/teaching/distancefunctions.pdf

More information

CMS winter meeting 2008, Ottawa. The heat kernel on connected sums

CMS winter meeting 2008, Ottawa. The heat kernel on connected sums CMS winter meeting 2008, Ottawa The heat kernel on connected sums Laurent Saloff-Coste (Cornell University) December 8 2008 p(t, x, y) = The heat kernel ) 1 x y 2 exp ( (4πt) n/2 4t The heat kernel is:

More information

Geometry and topology of continuous best and near best approximations

Geometry and topology of continuous best and near best approximations Journal of Approximation Theory 105: 252 262, Geometry and topology of continuous best and near best approximations Paul C. Kainen Dept. of Mathematics Georgetown University Washington, D.C. 20057 Věra

More information

Model Selection and Geometry

Model Selection and Geometry Model Selection and Geometry Pascal Massart Université Paris-Sud, Orsay Leipzig, February Purpose of the talk! Concentration of measure plays a fundamental role in the theory of model selection! Model

More information

Bayesian Nonparametric Point Estimation Under a Conjugate Prior

Bayesian Nonparametric Point Estimation Under a Conjugate Prior University of Pennsylvania ScholarlyCommons Statistics Papers Wharton Faculty Research 5-15-2002 Bayesian Nonparametric Point Estimation Under a Conjugate Prior Xuefeng Li University of Pennsylvania Linda

More information

Geometry of Ricci Solitons

Geometry of Ricci Solitons Geometry of Ricci Solitons H.-D. Cao, Lehigh University LMU, Munich November 25, 2008 1 Ricci Solitons A complete Riemannian (M n, g ij ) is a Ricci soliton if there exists a smooth function f on M such

More information

The Learning Problem and Regularization

The Learning Problem and Regularization 9.520 Class 02 February 2011 Computational Learning Statistical Learning Theory Learning is viewed as a generalization/inference problem from usually small sets of high dimensional, noisy data. Learning

More information

Handlebody Decomposition of a Manifold

Handlebody Decomposition of a Manifold Handlebody Decomposition of a Manifold Mahuya Datta Statistics and Mathematics Unit Indian Statistical Institute, Kolkata mahuya@isical.ac.in January 12, 2012 contents Introduction What is a handlebody

More information

21.1 Lower bounds on minimax risk for functional estimation

21.1 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 information

Hypothesis Testing via Convex Optimization

Hypothesis Testing via Convex Optimization Hypothesis Testing via Convex Optimization Arkadi Nemirovski Joint research with Alexander Goldenshluger Haifa University Anatoli Iouditski Grenoble University Information Theory, Learning and Big Data

More information

7 Complete metric spaces and function spaces

7 Complete metric spaces and function spaces 7 Complete metric spaces and function spaces 7.1 Completeness Let (X, d) be a metric space. Definition 7.1. A sequence (x n ) n N in X is a Cauchy sequence if for any ɛ > 0, there is N N such that n, m

More information

Econ Lecture 3. Outline. 1. Metric Spaces and Normed Spaces 2. Convergence of Sequences in Metric Spaces 3. Sequences in R and R n

Econ 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 information

Differential Privacy in an RKHS

Differential Privacy in an RKHS Differential Privacy in an RKHS Rob Hall (with Larry Wasserman and Alessandro Rinaldo) 2/20/2012 rjhall@cs.cmu.edu http://www.cs.cmu.edu/~rjhall 1 Overview Why care about privacy? Differential Privacy

More information

Lecture 8: Information Theory and Statistics

Lecture 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 information

4 Countability axioms

4 Countability axioms 4 COUNTABILITY AXIOMS 4 Countability axioms Definition 4.1. Let X be a topological space X is said to be first countable if for any x X, there is a countable basis for the neighborhoods of x. X is said

More information

Problem set 1, Real Analysis I, Spring, 2015.

Problem set 1, Real Analysis I, Spring, 2015. Problem set 1, Real Analysis I, Spring, 015. (1) Let f n : D R be a sequence of functions with domain D R n. Recall that f n f uniformly if and only if for all ɛ > 0, there is an N = N(ɛ) so that if n

More information

Coarse Geometry. Phanuel Mariano. Fall S.i.g.m.a. Seminar. Why Coarse Geometry? Coarse Invariants A Coarse Equivalence to R 1

Coarse Geometry. Phanuel Mariano. Fall S.i.g.m.a. Seminar. Why Coarse Geometry? Coarse Invariants A Coarse Equivalence to R 1 Coarse Geometry 1 1 University of Connecticut Fall 2014 - S.i.g.m.a. Seminar Outline 1 Motivation 2 3 The partition space P ([a, b]). Preliminaries Main Result 4 Outline Basic Problem 1 Motivation 2 3

More information

ON THE REGULARITY OF SAMPLE PATHS OF SUB-ELLIPTIC DIFFUSIONS ON MANIFOLDS

ON 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

Priors for the frequentist, consistency beyond Schwartz

Priors for the frequentist, consistency beyond Schwartz Victoria University, Wellington, New Zealand, 11 January 2016 Priors for the frequentist, consistency beyond Schwartz Bas Kleijn, KdV Institute for Mathematics Part I Introduction Bayesian and Frequentist

More information

Math 225A: Differential Topology, Final Exam

Math 225A: Differential Topology, Final Exam Math 225A: Differential Topology, Final Exam Ian Coley December 9, 2013 The goal is the following theorem. Theorem (Hopf). Let M be a compact n-manifold without boundary, and let f, g : M S n be two smooth

More information

A Glimpse into Topology

A Glimpse into Topology A Glimpse into Topology by Vishal Malik A project submitted to the Department of Mathematical Sciences in conformity with the requirements for Math 430 (203-4) Lakehead University Thunder Bay, Ontario,

More information

COUNTEREXAMPLES TO THE COARSE BAUM-CONNES CONJECTURE. Nigel Higson. Unpublished Note, 1999

COUNTEREXAMPLES TO THE COARSE BAUM-CONNES CONJECTURE. Nigel Higson. Unpublished Note, 1999 COUNTEREXAMPLES TO THE COARSE BAUM-CONNES CONJECTURE Nigel Higson Unpublished Note, 1999 1. Introduction Let X be a discrete, bounded geometry metric space. 1 Associated to X is a C -algebra C (X) which

More information

Homology through Interleaving

Homology through Interleaving Notes by Tamal K. Dey, OSU 91 Homology through Interleaving 32 Concept of interleaving A discrete set P R k is assumed to be a sample of a set X R k, if it lies near to it which we can quantify with the

More information

MA651 Topology. Lecture 10. Metric Spaces.

MA651 Topology. Lecture 10. Metric Spaces. MA65 Topology. Lecture 0. Metric Spaces. This text is based on the following books: Topology by James Dugundgji Fundamental concepts of topology by Peter O Neil Linear Algebra and Analysis by Marc Zamansky

More information

Introduction to Empirical Processes and Semiparametric Inference Lecture 08: Stochastic Convergence

Introduction 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 information

THESIS METRIC THICKENINGS OF EUCLIDEAN SUBMANIFOLDS. Submitted by. Joshua R. Mirth. Department of Mathematics

THESIS METRIC THICKENINGS OF EUCLIDEAN SUBMANIFOLDS. Submitted by. Joshua R. Mirth. Department of Mathematics THESIS METRIC THICKENINGS OF EUCLIDEAN SUBMANIFOLDS Submitted by Joshua R. Mirth Department of Mathematics In partial fulfillment of the requirements For the Degree of Master of Science Colorado State

More information

Local Asymptotic Normality in Quantum Statistics

Local Asymptotic Normality in Quantum Statistics Local Asymptotic Normality in Quantum Statistics M!d!lin Gu"! School of Mathematical Sciences University of Nottingham Richard Gill (Leiden) Jonas Kahn (Paris XI) Bas Janssens (Utrecht) Anna Jencova (Bratislava)

More information

Note: all spaces are assumed to be path connected and locally path connected.

Note: all spaces are assumed to be path connected and locally path connected. Homework 2 Note: all spaces are assumed to be path connected and locally path connected. 1: Let X be the figure 8 space. Precisely define a space X and a map p : X X which is the universal cover. Check

More information

121B: ALGEBRAIC TOPOLOGY. Contents. 6. Poincaré Duality

121B: ALGEBRAIC TOPOLOGY. Contents. 6. Poincaré Duality 121B: ALGEBRAIC TOPOLOGY Contents 6. Poincaré Duality 1 6.1. Manifolds 2 6.2. Orientation 3 6.3. Orientation sheaf 9 6.4. Cap product 11 6.5. Proof for good coverings 15 6.6. Direct limit 18 6.7. Proof

More information

Asymptotic Equivalence and Adaptive Estimation for Robust Nonparametric Regression

Asymptotic Equivalence and Adaptive Estimation for Robust Nonparametric Regression Asymptotic Equivalence and Adaptive Estimation for Robust Nonparametric Regression T. Tony Cai 1 and Harrison H. Zhou 2 University of Pennsylvania and Yale University Abstract Asymptotic equivalence theory

More information

arxiv:submit/ [math.st] 6 May 2011

arxiv:submit/ [math.st] 6 May 2011 A Continuous Mapping Theorem for the Smallest Argmax Functional arxiv:submit/0243372 [math.st] 6 May 2011 Emilio Seijo and Bodhisattva Sen Columbia University Abstract This paper introduces a version of

More information

Gromov s Proof of Mostow Rigidity

Gromov s Proof of Mostow Rigidity Gromov s Proof of Mostow Rigidity Mostow Rigidity is a theorem about invariants. An invariant assigns a label to whatever mathematical object I am studying that is well-defined up to the appropriate equivalence.

More information

Statistical Measures of Uncertainty in Inverse Problems

Statistical Measures of Uncertainty in Inverse Problems Statistical Measures of Uncertainty in Inverse Problems Workshop on Uncertainty in Inverse Problems Institute for Mathematics and Its Applications Minneapolis, MN 19-26 April 2002 P.B. Stark Department

More information

16.1 Bounding Capacity with Covering Number

16.1 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 information

Manifold Regularization

Manifold Regularization 9.520: Statistical Learning Theory and Applications arch 3rd, 200 anifold Regularization Lecturer: Lorenzo Rosasco Scribe: Hooyoung Chung Introduction In this lecture we introduce a class of learning algorithms,

More information

Math General Topology Fall 2012 Homework 13 Solutions

Math General Topology Fall 2012 Homework 13 Solutions Math 535 - General Topology Fall 2012 Homework 13 Solutions Note: In this problem set, function spaces are endowed with the compact-open topology unless otherwise noted. Problem 1. Let X be a compact topological

More information

Algebraic Topology European Mathematical Society Zürich 2008 Tammo tom Dieck Georg-August-Universität

Algebraic Topology European Mathematical Society Zürich 2008 Tammo tom Dieck Georg-August-Universität 1 Algebraic Topology European Mathematical Society Zürich 2008 Tammo tom Dieck Georg-August-Universität Corrections for the first printing Page 7 +6: j is already assumed to be an inclusion. But the assertion

More information

l 1 -Regularized Linear Regression: Persistence and Oracle Inequalities

l 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 information

How hard is this function to optimize?

How 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 information

An inverse of Sanov s theorem

An inverse of Sanov s theorem An inverse of Sanov s theorem Ayalvadi Ganesh and Neil O Connell BRIMS, Hewlett-Packard Labs, Bristol Abstract Let X k be a sequence of iid random variables taking values in a finite set, and consider

More information

Chapter 4: Asymptotic Properties of the MLE

Chapter 4: Asymptotic Properties of the MLE Chapter 4: Asymptotic Properties of the MLE Daniel O. Scharfstein 09/19/13 1 / 1 Maximum Likelihood Maximum likelihood is the most powerful tool for estimation. In this part of the course, we will consider

More information

Spectral applications of metric surgeries

Spectral applications of metric surgeries Spectral applications of metric surgeries Pierre Jammes Neuchâtel, june 2013 Introduction and motivations Examples of applications of metric surgeries Let (M n, g) be a closed riemannian manifold, and

More information

ABSOLUTE CONTINUITY OF FOLIATIONS

ABSOLUTE CONTINUITY OF FOLIATIONS ABSOLUTE CONTINUITY OF FOLIATIONS C. PUGH, M. VIANA, A. WILKINSON 1. Introduction In what follows, U is an open neighborhood in a compact Riemannian manifold M, and F is a local foliation of U. By this

More information

arxiv: v3 [math.ds] 9 Nov 2012

arxiv: v3 [math.ds] 9 Nov 2012 Positive expansive flows Alfonso Artigue November 13, 2018 arxiv:1210.3202v3 [math.ds] 9 Nov 2012 Abstract We show that every positive expansive flow on a compact metric space consists of a finite number

More information

Statistical inference on Lévy processes

Statistical inference on Lévy processes Alberto Coca Cabrero University of Cambridge - CCA Supervisors: Dr. Richard Nickl and Professor L.C.G.Rogers Funded by Fundación Mutua Madrileña and EPSRC MASDOC/CCA student workshop 2013 26th March Outline

More information

Discussion of Hypothesis testing by convex optimization

Discussion of Hypothesis testing by convex optimization Electronic Journal of Statistics Vol. 9 (2015) 1 6 ISSN: 1935-7524 DOI: 10.1214/15-EJS990 Discussion of Hypothesis testing by convex optimization Fabienne Comte, Céline Duval and Valentine Genon-Catalot

More information

Dynamics of Group Actions and Minimal Sets

Dynamics of Group Actions and Minimal Sets University of Illinois at Chicago www.math.uic.edu/ hurder First Joint Meeting of the Sociedad de Matemática de Chile American Mathematical Society Special Session on Group Actions: Probability and Dynamics

More information

Closed characteristics on non-compact mechanical contact manifolds 1

Closed characteristics on non-compact mechanical contact manifolds 1 Closed characteristics on non-compact mechanical contact manifolds Jan Bouwe van den Berg, Federica Pasquotto, Thomas O. Rot and Robert C.A.M. Vandervorst Department of Mathematics, VU Universiteit Amsterdam,

More information

Graph Induced Complex: A Data Sparsifier for Homology Inference

Graph Induced Complex: A Data Sparsifier for Homology Inference Graph Induced Complex: A Data Sparsifier for Homology Inference Tamal K. Dey Fengtao Fan Yusu Wang Department of Computer Science and Engineering The Ohio State University October, 2013 Space, Sample and

More information

Lecture I: Asymptotics for large GUE random matrices

Lecture I: Asymptotics for large GUE random matrices Lecture I: Asymptotics for large GUE random matrices Steen Thorbjørnsen, University of Aarhus andom Matrices Definition. Let (Ω, F, P) be a probability space and let n be a positive integer. Then a random

More information

PICARD S THEOREM STEFAN FRIEDL

PICARD S THEOREM STEFAN FRIEDL PICARD S THEOREM STEFAN FRIEDL Abstract. We give a summary for the proof of Picard s Theorem. The proof is for the most part an excerpt of [F]. 1. Introduction Definition. Let U C be an open subset. A

More information

Math212a1411 Lebesgue measure.

Math212a1411 Lebesgue measure. Math212a1411 Lebesgue measure. October 14, 2014 Reminder No class this Thursday Today s lecture will be devoted to Lebesgue measure, a creation of Henri Lebesgue, in his thesis, one of the most famous

More information

fy (X(g)) Y (f)x(g) gy (X(f)) Y (g)x(f)) = fx(y (g)) + gx(y (f)) fy (X(g)) gy (X(f))

fy (X(g)) Y (f)x(g) gy (X(f)) Y (g)x(f)) = fx(y (g)) + gx(y (f)) fy (X(g)) gy (X(f)) 1. Basic algebra of vector fields Let V be a finite dimensional vector space over R. Recall that V = {L : V R} is defined to be the set of all linear maps to R. V is isomorphic to V, but there is no canonical

More information

Eilenberg-Steenrod properties. (Hatcher, 2.1, 2.3, 3.1; Conlon, 2.6, 8.1, )

Eilenberg-Steenrod properties. (Hatcher, 2.1, 2.3, 3.1; Conlon, 2.6, 8.1, ) II.3 : Eilenberg-Steenrod properties (Hatcher, 2.1, 2.3, 3.1; Conlon, 2.6, 8.1, 8.3 8.5 Definition. Let U be an open subset of R n for some n. The de Rham cohomology groups (U are the cohomology groups

More information

Nonparametric regression for topology. applied to brain imaging data

Nonparametric regression for topology. applied to brain imaging data , applied to brain imaging data Cleveland State University October 15, 2010 Motivation from Brain Imaging MRI Data Topology Statistics Application MRI Data Topology Statistics Application Cortical surface

More information

POINTWISE BOUNDS ON QUASIMODES OF SEMICLASSICAL SCHRÖDINGER OPERATORS IN DIMENSION TWO

POINTWISE BOUNDS ON QUASIMODES OF SEMICLASSICAL SCHRÖDINGER OPERATORS IN DIMENSION TWO POINTWISE BOUNDS ON QUASIMODES OF SEMICLASSICAL SCHRÖDINGER OPERATORS IN DIMENSION TWO HART F. SMITH AND MACIEJ ZWORSKI Abstract. We prove optimal pointwise bounds on quasimodes of semiclassical Schrödinger

More information

Math General Topology Fall 2012 Homework 8 Solutions

Math General Topology Fall 2012 Homework 8 Solutions Math 535 - General Topology Fall 2012 Homework 8 Solutions Problem 1. (Willard Exercise 19B.1) Show that the one-point compactification of R n is homeomorphic to the n-dimensional sphere S n. Note that

More information