Appendix to: On the Relation Between Low Density Separation, Spectral Clustering and Graph Cuts
|
|
- Maud Tate
- 5 years ago
- Views:
Transcription
1 Appendix to: On the Relation Between Low Density Separation, Spectral Clustering and Graph Cuts Hariharan Narayanan Department of Computer Science University of Chicago Chicago IL 6637 ikhail Belkin Department of Computer Science and Engineering The Ohio State University Columbus, OH 43 Partha Niyogi Department of Computer Science University of Chicago Chicago IL 6637 A Regularity conditions on p and S We make the following assumptions about p:. p can be extended to a function p that is L Lipshitz and which is bounded above by p max.. For < t < t, min(p(x), K t (x, y)p(y)dy) p min. Note that this is a property of both of the boundary and p. We note that since p is L Lipshitz over R d, so is K t(x, z)p (z)dz. We assume that S has condition number /τ. We also make the following assumption about S:- The volume of the set of points whose distance to both S and is R, is O(R ) as R. This is reasonable, and is true if S is a manifold of codimension. B Proof of Theorem This follows from Theorem 4 (which is proved in a later section), by setting µ to be equal to ɛ d+. C Proof of Theorem In the proof we will use a generalization of cdiarmid s inequality from [7, 8]. We start with the with the following Definition Let Ω,..., Ω m be probability spaces. Let Ω = m Ω k and let Y be a random variable on Ω. We say that Y is strongly difference-bounded by (b, c, δ) if the following holds: there is a bad subset B Ω, where δ = Pr(ω B). If ω, ω Ω differ only in the kth coordinate, and ω B, then Y (ω) Y (ω ) c.
2 Furthermore, for any ω and ω differing only in the kth coordinate, Y (ω) Y (ω ) b. Theorem ([7, 8]) Let Ω,..., Ω m be probability spaces. Let Ω = m Ω k and let Y be a random variable on Ω which is strongly difference-bounded by (b, c, δ). Assume b c >. Let µ = E(Y ). Then for any r >, By Hoeffding s inequality P [ z x K t(x, z) N Pr( Y µ r) ( exp ( r 8mc ) + mbδ c ). E(K t (x, z)) > ɛ E(K t (x, z))] < e (N )E(Kt(x,z)) ɛ t e (N )p min ɛ t. We set ɛ to be t /N µ. Let e (N )p min ɛ t be δ/n. By the union bound, the probability that the above event happens for some x X is δ. The set of all ω Ω for which this occurs shall be denoted by B. Also, for any X, the largest possible value that /N π/t K t (x, y) {( y X z x K t(x, z))( z y K t(y, z))} / could take is π/t(n ). Then, x X E[β] α < ( ɛ ) α + δ π/t(n ). () Let q = (p min / t ). β is strongly difference-bounded by (b, c, δ) where c = O((qN t) ), b = O(N/ t). We now apply the generalization of cdiarmid s inequality in Theorem. Using the notation of Theorem, ( ( ) r Pr[ β E[β] > r] exp 8mc + Nbδ ) ( exp ( O(Nr q t) ) + O ( N 3 q exp ( O(Nqɛ c ) ))). () Putting this together with the relation between E[β] and α in (), the theorem is proved. We note that in (), the rate of convergence of E[β] to α is controlled by ɛ, which is t /N µ, and in (), the rate of convergence of β to E[β] depends on r, which we set to be t / tn µ. We note that in (), the dependence on r of the probability is exponential. Since we have assumed that u = t / (tn µ ) = o(), t /N µ = O(t d+ u). Thus the result follows. D Proof of Theorem 3 We shall prove theorem 3 through a sequence of lemmas. Without a loss of generality we can assume that τ = by rescaling, if necessary. Let R = dt ln(/t) and ɛ = z >R K t(, z)dx. Using the inequality ( ) d/ td K t (, z)dx R e R 4t + d = (et ln(/t)) d/ z >R (3)
3 E_ B_ O_ A H_ F_ R R R^ D_ G_ C Figure : A sphere of radius outside that is tangent to S A H_ F_ R C (R^)/ D_ G_ O_ B_ E_ Figure : A sphere of radius inside that is tangent to S we know that ɛ (et ln(/t)) d/. For any positive real t, ln(/t) t e. Therefore the assumption that ( ) t τ, (d) e e implies that R dt /e <. 3
4 Let the point y (represented as A in figures D and D) be at a distance r < R from. Let us choose a coordinate system where y = (r,,..., ) and the point nearest to it on is the origin. There is a unique such point since r < R <. Let this point be C. Let D lie on the segment AC, at a distance R / from C. Let D lie on the extended segment AC, at a distance R / from C. Thus C is the midpoint of D D. Definition. Denote the ball of radius tangent to at C that is outside by B.. Denote the ball of radius tangent to at C which is inside by B. 3. Let H be the halfspace containing C bounded by the hyperplane perpendicular to AC and passing through D. 4. Let H be the halfspace not containing C bounded by the hyperplane perpendicular to AC and passing through D. 5. Let H 3 be the halfspace not containing A, bounded by the hyperplane tangent to at C. 6. Let B be the ball with center y = A, whose boundary contains the intersection of H and B. 7. Let B be the ball with center y = A, whose boundary contains the intersection of H and B. Definition 3. h(r) := H 3 K t (x, y)dx.. f(r) := H B K t (x, y)dx. 3. g(r) := H B K t (x, y)dx. It follows that and K t (x, y)dx = h(r R /) H K t (x, y)dx = h(r + R /). H Observation Although h(r) is defined by an d-dimensional integral, this can be simplified to e (r x ) /4t h(r) = dx, 4πt by integrating out the coordinates x,..., x d. Lemma If r > R, the radius of B is R. x < Proof: By the similarity of triangles CF D and CE F in figure D, it follows that CF CE = CD CF. CE = and CD = R /. Therefore CF = R. Since CD F is right angled at D, and CD = R /, this proves the claim. Lemma The radius of B is R. Proof: By the similarity of triangles CF E and CD F in figure D CF = R. However, the distance of point y := A from F is CF. Therefore, the radius of B is R. Definition 4 Let the set of points x such that B(x, R) be denoted by. Let be S and S be S. Let =, be and S be. We shall denote ( + L/p min )R) by l. 4
5 Consider a point x, Then, K t (x, y)p(y)dy y x <R K t (x, y)p(y)dy ( ɛ)(p(x) LR) ( ɛ)p(x)( LR/p min ) = p(x)( O(l)) On the other hand, K t (x, y)p(y)dy K t (x, y)p(y)dy + K t (x, y)p(y)dy y x R y x >R p(x)( + l) + K t (, R) = p(x)( + O(( + L/p min )R)) Therefore, ψ t (x) = p(x)( ± O(( + L p min )R)). d Lemma 3 B(x, 5R) implies that dx Kt (x, z)p(z)dy = O(L). Proof: Consider the function p, which is equal to p on, but which has a larger support and is L Lipshitz as a function on R d. K t (x, z)p (z)dy is L Lipshitz and on points x where B(x, 5R), the contribution of points z outside, is o(). Therefore d dx Kt (x, z)p(z)dy = O(L). This implies that on the set of points x such that B(x, 5R), ψ t (X) is O(L) Lipshitz. We now estimate K t (y, z)p(z)dz for y S. Definition 5 For a point y S, such that d(y, ) < R < τ = let π(y) be the nearest point to y in S. Note that by the assumption that the condition number of S is, since R is smaller than, there is a unique candidate for π(y). Let y be as in Definition 5. Lemma 4 h(r + R /) ɛ < f(r) K t (y, z)dz. Proof: K t (x, y)dx > H B K t (x, y)dx(since H B ) K t (x, y)dx H > h(r + R /) ɛ B c K t (x, y)dx The last inequality follows from lemma. Lemma 5 > p(π(y))( O(l))(h(r + R /) ɛ). 5
6 Q P Q P Figure 3: The correspondence between points on and [ ] r Proof: (since H B ) H B > p(π(y))( O(l))(h(r + R /) ɛ). Lemma 6 Let r > R. Then, < ( + O(l))(h(r R /)p(π(y)) + ɛp max ). Proof: < R d B H R d B H B + B c < h(r R /)p(π(y))( + O(l)) + ɛp max ( + O(l)) < ( + O(l))(h(r R /)p(π(y)) + ɛp max ) The last inequality follows from lemma. Definition 6 Let [ ] r denote the set of points at a distance of r to [ ]. Let π r be map from [ ] r to [ ] that takes a point P on [ ] r to the foot of the perpendicular from P to. (This map is well-defined since r < τ =.) Lemma 7 Let y [ ] r. Let the Jacobian of a map f be denoted by Df. ( r) d Dπ r (y) ( + r) d. 6
7 Proof: Let P Q be a geodesic arc of infinitesimal length ds on joining P and Q. Let πr (P ) = P and πr (Q) = Q (see Figure D.) The radius of curvature of P Q is. Therefore the distance between P and Q is in the interval [ds( r), ds( + r)]. This implies that the Jacobian of the map π r has a magnitude that is always in the interval [( + r) d, ( r) d ]. Lemma 8 Proof: R d [ ] R dy ɛvol p max ( + O(l)). dy = R d [] R K t (x, y)ψ t (x)ψ t (y)dydx R d [S ] R K t (, z)p max ( + O(l))dzdx z >R < vol p max ( + O(l)). in line holds because the distance between x and y in the double integral is always R. Lemma 9 ( e α /4t ) π/t α h(r)dr π/t. Proof: Using observation, Setting y x := r, this becomes α r h(r)dr = aking the substitution r α := z, we have α α α e (x y ) /4t 4πt dx dy. e r /4t e r /4t dy dr = (r α)dr. 4πt α 4πt e (z+α) /4t 4πt zdz = e α /4t e z /4t zdz 4πt t π e α /4t Equality holds in the above calculation if and only if α =. Hence the proof is complete. Definition 7 Let [S ] [ ] r be r. Let [S ] [ ] r be r and [S ] [ ] r be r. We assume that vol( R ) < C R for some absolute constant C. Since the thickness of ( R ) is O(R) in two dimensions, this is a reasonable assumption to make. The assumption that has a d dimensional volume implies that vol = O(R). Putting these together to prove Theorem 3: 7
8 dy = dydr r O(p max/p min ) K t (x, y)dxdydr r ( R ) O(p max/p min ) K t (x, y)dxdydr + volsɛ r O(p max/p min ) ( vol ( R ) + ɛvol ). O(p max/p min ) ( C t µ + O(t µ vol ) ) S dy = dydr r R = ( dydr) r S + ( dydr) R r R ( dydr) r + ɛvol p max ( + O(l)). }{{} E (from lemma 8) R p max ( + O(l))dydr r R + ( + O(l))(h(r R /)p(π(y) + ɛp max )) + E R r The last line follows from Lemma 6. E + R ( + R ) d p max ( + O(l))vol ( )dr(from lemma 7) R + ( + R) d ( + O(l))( h(r)dr p(y)dy + ɛp max R). ( + O(l))( t/π p(y)dy + p max ((R + ɛr)vol ( ) + ɛvol )). ( + O(l))( p(y)dy( t/π + p max o(t µ )) + p max ɛvol ) p min Similarly, we see that S dy 8
9 = dydr r R > ( dydr) r R > p(π(y))( + O(l))f(r)dxdr r R > ( R) d ( O(l))( p(y)dy)(h(r + R /) ɛ)dr R > ( R) d ( O(( L/p min )R))( p(y)dy)(( (h(r)dr) ɛr R /) ( O(l))( p(y)dy)(( e R /4t ) t/π ɛr R /) ( O(l))( p(y)dy)( t/π o(t µ )). Noting only the dependence of the rate on t, and introducing the condition number τ, π ) dy = ( + o((t/τ )) µ t S S p(s)ds. Proof of Theorem 4: This follows directly from Theorem and Theorem 3. The only change made was that the t d+ term was eliminated since it is dominated by t ɛ when t is small. References []. Belkin and P. Niyogi (4). Semi-supervised Learning on Riemannian anifolds. In achine Learning 56, Special Issue on Clustering, []. Belkin and P. Niyogi. Toward a theoretical foundation for Laplacian-based manifold methods. COLT 5. [3] A. Blum and S. Chawla, Learning from labeled and unlabeled data using graph mincuts, ICL. [4] O.Chapelle, J. Weston, B. Scholkopf, Cluster kernels for semi-supervised learning, NIPS. [5] O. Chapelle and A. Zien, Semi-supervised Classification by Low Density Separation, AISTATS 5. [6] Chris Ding, Spectral Clustering, ICL 4 Tutorial. [7] Samuel Kutin, Partha Niyogi, Almost-everywhere Algorithmic Stability and Generalization Error., UAI, 75-8 [8] S. Kutin, TR--4, Extensions to cdiarmid s inequality when differences are bounded with high probability. Technical report TR--4 at the Department of Computer Science, University of Chicago. [9] S. Lafon, Diffusion aps and Geodesic Harmonics, Ph. D. Thesis, Yale University, 4. []. Hein, J.-Y. Audibert, U. von Luxburg, From Graphs to anifolds Weak and Strong Pointwise Consistency of Graph Laplacians, COLT 5. [] J. Shi and J. alik. Normalized cuts and image segmentation. [] U. von Luxburg,. Belkin, O. Bousquet, Consistency of Spectral Clustering, ax Planck Institute for Biological Cybernetics Technical Report TR 34, 4. [3] X. Zhu, J. Lafferty and Z. Ghahramani, Semi-supervised learning using Gaussian fields and harmonic functions, ICL 3. 9
Graphs, Geometry and Semi-supervised Learning
Graphs, Geometry and Semi-supervised Learning Mikhail Belkin The Ohio State University, Dept of Computer Science and Engineering and Dept of Statistics Collaborators: Partha Niyogi, Vikas Sindhwani In
More informationLearning from Labeled and Unlabeled Data: Semi-supervised Learning and Ranking p. 1/31
Learning from Labeled and Unlabeled Data: Semi-supervised Learning and Ranking Dengyong Zhou zhou@tuebingen.mpg.de Dept. Schölkopf, Max Planck Institute for Biological Cybernetics, Germany Learning from
More informationFrom graph to manifold Laplacian: The convergence rate
Appl. Comput. Harmon. Anal. 2 (2006) 28 34 www.elsevier.com/locate/acha Letter to the Editor From graph to manifold Laplacian: The convergence rate A. Singer Department of athematics, Yale University,
More informationLimits of Spectral Clustering
Limits of Spectral Clustering Ulrike von Luxburg and Olivier Bousquet Max Planck Institute for Biological Cybernetics Spemannstr. 38, 72076 Tübingen, Germany {ulrike.luxburg,olivier.bousquet}@tuebingen.mpg.de
More informationGraph-Based Semi-Supervised Learning
Graph-Based Semi-Supervised Learning Olivier Delalleau, Yoshua Bengio and Nicolas Le Roux Université de Montréal CIAR Workshop - April 26th, 2005 Graph-Based Semi-Supervised Learning Yoshua Bengio, Olivier
More informationHow to learn from very few examples?
How to learn from very few examples? Dengyong Zhou Department of Empirical Inference Max Planck Institute for Biological Cybernetics Spemannstr. 38, 72076 Tuebingen, Germany Outline Introduction Part A
More informationUniform convergence of adaptive graph-based regularization
Uniform convergence of adaptive graph-based regularization atthias Hein ax Planck Institute for Biological Cybernetics, Tübingen, Germany Abstract. The regularization functional induced by the graph Laplacian
More informationJustin Solomon MIT, Spring 2017
Justin Solomon MIT, Spring 2017 http://pngimg.com/upload/hammer_png3886.png You can learn a lot about a shape by hitting it (lightly) with a hammer! What can you learn about its shape from vibration frequencies
More informationAnalysis of Spectral Kernel Design based Semi-supervised Learning
Analysis of Spectral Kernel Design based Semi-supervised Learning Tong Zhang IBM T. J. Watson Research Center Yorktown Heights, NY 10598 Rie Kubota Ando IBM T. J. Watson Research Center Yorktown Heights,
More informationSemi-Supervised Learning with the Graph Laplacian: The Limit of Infinite Unlabelled Data
Semi-Supervised Learning with the Graph Laplacian: The Limit of Infinite Unlabelled Data Boaz Nadler Dept. of Computer Science and Applied Mathematics Weizmann Institute of Science Rehovot, Israel 76 boaz.nadler@weizmann.ac.il
More informationIFT LAPLACIAN APPLICATIONS. Mikhail Bessmeltsev
IFT 6112 09 LAPLACIAN APPLICATIONS http://www-labs.iro.umontreal.ca/~bmpix/teaching/6112/2018/ Mikhail Bessmeltsev Rough Intuition http://pngimg.com/upload/hammer_png3886.png You can learn a lot about
More informationDiffusion Maps, Spectral Clustering and Eigenfunctions of Fokker-Planck Operators
Diffusion Maps, Spectral Clustering and Eigenfunctions of Fokker-Planck Operators Boaz Nadler Stéphane Lafon Ronald R. Coifman Department of Mathematics, Yale University, New Haven, CT 652. {boaz.nadler,stephane.lafon,ronald.coifman}@yale.edu
More informationSemi-supervised Learning using Sparse Eigenfunction Bases
Semi-supervised Learning using Sparse Eigenfunction Bases Kaushik Sinha Dept. of Computer Science and Engineering Ohio State University Columbus, OH 43210 sinhak@cse.ohio-state.edu Mikhail Belkin Dept.
More informationAn Analysis of the Convergence of Graph Laplacians
Daniel Ting Department of Statistics, UC Berkeley Ling Huang Intel Labs Berkeley Michael I. Jordan Department of EECS and Statistics, UC Berkeley dting@stat.berkeley.edu ling.huang@intel.com jordan@cs.berkeley.edu
More informationContribution from: Springer Verlag Berlin Heidelberg 2005 ISBN
Contribution from: Mathematical Physics Studies Vol. 7 Perspectives in Analysis Essays in Honor of Lennart Carleson s 75th Birthday Michael Benedicks, Peter W. Jones, Stanislav Smirnov (Eds.) Springer
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 informationData Analysis and Manifold Learning Lecture 7: Spectral Clustering
Data Analysis and Manifold Learning Lecture 7: Spectral Clustering Radu Horaud INRIA Grenoble Rhone-Alpes, France Radu.Horaud@inrialpes.fr http://perception.inrialpes.fr/ Outline of Lecture 7 What is spectral
More informationAdd Math (4047/02) Year t years $P
Add Math (4047/0) Requirement : Answer all questions Total marks : 100 Duration : hour 30 minutes 1. The price, $P, of a company share on 1 st January has been increasing each year from 1995 to 015. The
More informationManifold Denoising. Matthias Hein Markus Maier Max Planck Institute for Biological Cybernetics Tübingen, Germany
Manifold Denoising Matthias Hein Markus Maier Max Planck Institute for Biological Cybernetics Tübingen, Germany {first.last}@tuebingen.mpg.de Abstract We consider the problem of denoising a noisily sampled
More informationSemi-Supervised Learning in Reproducing Kernel Hilbert Spaces Using Local Invariances
Semi-Supervised Learning in Reproducing Kernel Hilbert Spaces Using Local Invariances Wee Sun Lee,2, Xinhua Zhang,2, and Yee Whye Teh Department of Computer Science, National University of Singapore. 2
More informationRegularizing objective functionals in semi-supervised learning
Regularizing objective functionals in semi-supervised learning Dejan Slepčev Carnegie Mellon University February 9, 2018 1 / 47 References S,Thorpe, Analysis of p-laplacian regularization in semi-supervised
More information2. Metric Spaces. 2.1 Definitions etc.
2. Metric Spaces 2.1 Definitions etc. The procedure in Section for regarding R as a topological space may be generalized to many other sets in which there is some kind of distance (formally, sets with
More informationOn the Convergence of Spectral Clustering on Random Samples: the Normalized Case
On the Convergence of Spectral Clustering on Random Samples: the Normalized Case Ulrike von Luxburg 1, Olivier Bousquet 1, and Mikhail Belkin 2 1 Max Planck Institute for Biological Cybernetics, Tübingen,
More informationThe crucial role of statistics in manifold learning
The crucial role of statistics in manifold learning Tyrus Berry Postdoc, Dept. of Mathematical Sciences, GMU Statistics Seminar GMU Feb., 26 Postdoctoral position supported by NSF ANALYSIS OF POINT CLOUDS
More informationSemi-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 informationA graph based approach to semi-supervised learning
A graph based approach to semi-supervised learning 1 Feb 2011 Two papers M. Belkin, P. Niyogi, and V Sindhwani. Manifold regularization: a geometric framework for learning from labeled and unlabeled examples.
More informationActive and Semi-supervised Kernel Classification
Active and Semi-supervised Kernel Classification Zoubin Ghahramani Gatsby Computational Neuroscience Unit University College London Work done in collaboration with Xiaojin Zhu (CMU), John Lafferty (CMU),
More informationLaplacian Eigenmaps for Dimensionality Reduction and Data Representation
Introduction and Data Representation Mikhail Belkin & Partha Niyogi Department of Electrical Engieering University of Minnesota Mar 21, 2017 1/22 Outline Introduction 1 Introduction 2 3 4 Connections to
More informationBack to the future: Radial Basis Function networks revisited
Back to the future: Radial Basis Function networks revisited Qichao Que, Mikhail Belkin Department of Computer Science and Engineering Ohio State University Columbus, OH 4310 que, mbelkin@cse.ohio-state.edu
More informationSemi-Supervised Learning with Graphs
Semi-Supervised Learning with Graphs Xiaojin (Jerry) Zhu LTI SCS CMU Thesis Committee John Lafferty (co-chair) Ronald Rosenfeld (co-chair) Zoubin Ghahramani Tommi Jaakkola 1 Semi-supervised Learning classifiers
More informationSemi-Supervised Learning
Semi-Supervised Learning getting more for less in natural language processing and beyond Xiaojin (Jerry) Zhu School of Computer Science Carnegie Mellon University 1 Semi-supervised Learning many human
More informationGlobal vs. Multiscale Approaches
Harmonic Analysis on Graphs Global vs. Multiscale Approaches Weizmann Institute of Science, Rehovot, Israel July 2011 Joint work with Matan Gavish (WIS/Stanford), Ronald Coifman (Yale), ICML 10' Challenge:
More informationParadoxical Euler: Integrating by Differentiating. Andrew Fabian Hieu D. Nguyen. Department of Mathematics Rowan University, Glassboro, NJ 08028
Paradoxical Euler: Integrating by Differentiating Andrew Fabian Hieu D Nguyen Department of Mathematics Rowan University, Glassboro, NJ 0808 3-3-09 I Introduction Every student of calculus learns that
More informationSemi-Supervised Learning with Graphs. Xiaojin (Jerry) Zhu School of Computer Science Carnegie Mellon University
Semi-Supervised Learning with Graphs Xiaojin (Jerry) Zhu School of Computer Science Carnegie Mellon University 1 Semi-supervised Learning classification classifiers need labeled data to train labeled data
More informationGeometry on Probability Spaces
Geometry on Probability Spaces Steve Smale Toyota Technological Institute at Chicago 427 East 60th Street, Chicago, IL 60637, USA E-mail: smale@math.berkeley.edu Ding-Xuan Zhou Department of Mathematics,
More informationBeyond Scalar Affinities for Network Analysis or Vector Diffusion Maps and the Connection Laplacian
Beyond Scalar Affinities for Network Analysis or Vector Diffusion Maps and the Connection Laplacian Amit Singer Princeton University Department of Mathematics and Program in Applied and Computational Mathematics
More informationTHE HIDDEN CONVEXITY OF SPECTRAL CLUSTERING
THE HIDDEN CONVEXITY OF SPECTRAL CLUSTERING Luis Rademacher, Ohio State University, Computer Science and Engineering. Joint work with Mikhail Belkin and James Voss This talk A new approach to multi-way
More informationDiscrete vs. Continuous: Two Sides of Machine Learning
Discrete vs. Continuous: Two Sides of Machine Learning Dengyong Zhou Department of Empirical Inference Max Planck Institute for Biological Cybernetics Spemannstr. 38, 72076 Tuebingen, Germany Oct. 18,
More informationKUIPER S THEOREM ON CONFORMALLY FLAT MANIFOLDS
KUIPER S THEOREM ON CONFORMALLY FLAT MANIFOLDS RALPH HOWARD DEPARTMENT OF MATHEMATICS UNIVERSITY OF SOUTH CAROLINA COLUMBIA, S.C. 29208, USA HOWARD@MATH.SC.EDU 1. Introduction These are notes to that show
More informationSpectral Clustering. Zitao Liu
Spectral Clustering Zitao Liu Agenda Brief Clustering Review Similarity Graph Graph Laplacian Spectral Clustering Algorithm Graph Cut Point of View Random Walk Point of View Perturbation Theory Point of
More informationAn Iterated Graph Laplacian Approach for Ranking on Manifolds
An Iterated Graph Laplacian Approach for Ranking on Manifolds Xueyuan Zhou Department of Computer Science University of Chicago Chicago, IL zhouxy@cs.uchicago.edu Mikhail Belkin Department of Computer
More informationMarch 13, Paper: R.R. Coifman, S. Lafon, Diffusion maps ([Coifman06]) Seminar: Learning with Graphs, Prof. Hein, Saarland University
Kernels March 13, 2008 Paper: R.R. Coifman, S. Lafon, maps ([Coifman06]) Seminar: Learning with Graphs, Prof. Hein, Saarland University Kernels Figure: Example Application from [LafonWWW] meaningful geometric
More informationSemi-Supervised Learning on Riemannian Manifolds
Machine Learning, 56, 209 239, 2004 c 2004 Kluwer Academic Publishers. Manufactured in The Netherlands. Semi-Supervised Learning on Riemannian Manifolds MIKHAIL BELKIN misha@math.uchicago.edu PARTHA NIYOGI
More informationThe Minimal Element Theorem
The Minimal Element Theorem The CMC Dynamics Theorem deals with describing all of the periodic or repeated geometric behavior of a properly embedded CMC surface with bounded second fundamental form in
More informationSpectral Clustering. Spectral Clustering? Two Moons Data. Spectral Clustering Algorithm: Bipartioning. Spectral methods
Spectral Clustering Seungjin Choi Department of Computer Science POSTECH, Korea seungjin@postech.ac.kr 1 Spectral methods Spectral Clustering? Methods using eigenvectors of some matrices Involve eigen-decomposition
More informationKing Fahd University of Petroleum and Minerals Prep-Year Math Program Math (001) - Term 181 Recitation (1.1)
Recitation (1.1) Question 1: Find a point on the y-axis that is equidistant from the points (5, 5) and (1, 1) Question 2: Find the distance between the points P(2 x, 7 x) and Q( 2 x, 4 x) where x 0. Question
More information1 First and second variational formulas for area
1 First and second variational formulas for area In this chapter, we will derive the first and second variational formulas for the area of a submanifold. This will be useful in our later discussion on
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 informationContents. MATH 32B-2 (18W) (L) G. Liu / (TA) A. Zhou Calculus of Several Variables. 1 Multiple Integrals 3. 2 Vector Fields 9
MATH 32B-2 (8W) (L) G. Liu / (TA) A. Zhou Calculus of Several Variables Contents Multiple Integrals 3 2 Vector Fields 9 3 Line and Surface Integrals 5 4 The Classical Integral Theorems 9 MATH 32B-2 (8W)
More informationSemi-Supervised Learning through Principal Directions Estimation
Semi-Supervised Learning through Principal Directions Estimation Olivier Chapelle, Bernhard Schölkopf, Jason Weston Max Planck Institute for Biological Cybernetics, 72076 Tübingen, Germany {first.last}@tuebingen.mpg.de
More informationPractice Final Solutions
Practice Final Solutions Math 1, Fall 17 Problem 1. Find a parameterization for the given curve, including bounds on the parameter t. Part a) The ellipse in R whose major axis has endpoints, ) and 6, )
More informationy mx 25m 25 4 circle. Then the perpendicular distance of tangent from the centre (0, 0) is the radius. Since tangent
Mathematics. The sides AB, BC and CA of ABC have, 4 and 5 interior points respectively on them as shown in the figure. The number of triangles that can be formed using these interior points is () 80 ()
More informationManifold 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 informationIYGB. Special Paper U. Time: 3 hours 30 minutes. Created by T. Madas. Created by T. Madas
IYGB Special Paper U Time: 3 hours 30 minutes Candidates may NOT use any calculator Information for Candidates This practice paper follows the Advanced Level Mathematics Core Syllabus Booklets of Mathematical
More informationSpectral Techniques for Clustering
Nicola Rebagliati 1/54 Spectral Techniques for Clustering Nicola Rebagliati 29 April, 2010 Nicola Rebagliati 2/54 Thesis Outline 1 2 Data Representation for Clustering Setting Data Representation and Methods
More informationRandom Walks on Hyperbolic Groups III
Random Walks on Hyperbolic Groups III Steve Lalley University of Chicago January 2014 Hyperbolic Groups Definition, Examples Geometric Boundary Ledrappier-Kaimanovich Formula Martin Boundary of FRRW on
More informationfor all subintervals I J. If the same is true for the dyadic subintervals I D J only, we will write ϕ BMO d (J). In fact, the following is true
3 ohn Nirenberg inequality, Part I A function ϕ L () belongs to the space BMO() if sup ϕ(s) ϕ I I I < for all subintervals I If the same is true for the dyadic subintervals I D only, we will write ϕ BMO
More informationLECTURE 15-16: PROPER ACTIONS AND ORBIT SPACES
LECTURE 15-16: PROPER ACTIONS AND ORBIT SPACES 1. Proper actions Suppose G acts on M smoothly, and m M. Then the orbit of G through m is G m = {g m g G}. If m, m lies in the same orbit, i.e. m = g m for
More informationGraphs in Machine Learning
Graphs in Machine Learning Michal Valko Inria Lille - Nord Europe, France TA: Pierre Perrault Partially based on material by: Mikhail Belkin, Jerry Zhu, Olivier Chapelle, Branislav Kveton October 30, 2017
More informationRandom Walks, Random Fields, and Graph Kernels
Random Walks, Random Fields, and Graph Kernels John Lafferty School of Computer Science Carnegie Mellon University Based on work with Avrim Blum, Zoubin Ghahramani, Risi Kondor Mugizi Rwebangira, Jerry
More informationExtensions to McDiarmid s inequality when differences are bounded with high probability
Extensions to McDiarmid s inequality when differences are bounded with high probability Samuel Kutin April 12, 2002 Abstract The method of independent bounded differences McDiarmid, 1989) gives largedeviation
More information(D) (A) Q.3 To which of the following circles, the line y x + 3 = 0 is normal at the point ? 2 (A) 2
CIRCLE [STRAIGHT OBJECTIVE TYPE] Q. The line x y + = 0 is tangent to the circle at the point (, 5) and the centre of the circles lies on x y = 4. The radius of the circle is (A) 3 5 (B) 5 3 (C) 5 (D) 5
More informationRigidity and Non-rigidity Results on the Sphere
Rigidity and Non-rigidity Results on the Sphere Fengbo Hang Xiaodong Wang Department of Mathematics Michigan State University Oct., 00 1 Introduction It is a simple consequence of the maximum principle
More informationB. Appendix B. Topological vector spaces
B.1 B. Appendix B. Topological vector spaces B.1. Fréchet spaces. In this appendix we go through the definition of Fréchet spaces and their inductive limits, such as they are used for definitions of function
More informationEfficient Iterative Semi-Supervised Classification on Manifold
Efficient Iterative Semi-Supervised Classification on Manifold Mehrdad Farajtabar, Hamid R. Rabiee, Amirreza Shaban, Ali Soltani-Farani Digital Media Lab, AICTC Research Center, Department of Computer
More informationThe prototypes of smooth manifolds
The prototypes of smooth manifolds The prototype smooth manifolds are the open subsets of R n. If U is an open subset of R n, a smooth map from U to R m is an m-tuple of real valued functions (f 1, f 2,...,
More informationManifold Regularization
Manifold Regularization Vikas Sindhwani Department of Computer Science University of Chicago Joint Work with Mikhail Belkin and Partha Niyogi TTI-C Talk September 14, 24 p.1 The Problem of Learning is
More informationAdvances in Manifold Learning Presented by: Naku Nak l Verm r a June 10, 2008
Advances in Manifold Learning Presented by: Nakul Verma June 10, 008 Outline Motivation Manifolds Manifold Learning Random projection of manifolds for dimension reduction Introduction to random projections
More informationJoint distribution optimal transportation for domain adaptation
Joint distribution optimal transportation for domain adaptation Changhuang Wan Mechanical and Aerospace Engineering Department The Ohio State University March 8 th, 2018 Joint distribution optimal transportation
More informationOnline Manifold Regularization: A New Learning Setting and Empirical Study
Online Manifold Regularization: A New Learning Setting and Empirical Study Andrew B. Goldberg 1, Ming Li 2, Xiaojin Zhu 1 1 Computer Sciences, University of Wisconsin Madison, USA. {goldberg,jerryzhu}@cs.wisc.edu
More informationMATH 425, FINAL EXAM SOLUTIONS
MATH 425, FINAL EXAM SOLUTIONS Each exercise is worth 50 points. Exercise. a The operator L is defined on smooth functions of (x, y by: Is the operator L linear? Prove your answer. L (u := arctan(xy u
More informationINVERSION IN THE PLANE BERKELEY MATH CIRCLE
INVERSION IN THE PLANE BERKELEY MATH CIRCLE ZVEZDELINA STANKOVA MILLS COLLEGE/UC BERKELEY SEPTEMBER 26TH 2004 Contents 1. Definition of Inversion in the Plane 1 Properties of Inversion 2 Problems 2 2.
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 informationLecture 5: Probabilistic tools and Applications II
T-79.7003: Graphs and Networks Fall 2013 Lecture 5: Probabilistic tools and Applications II Lecturer: Charalampos E. Tsourakakis Oct. 11, 2013 5.1 Overview In the first part of today s lecture we will
More informationMAC Calculus II Spring Homework #6 Some Solutions.
MAC 2312-15931-Calculus II Spring 23 Homework #6 Some Solutions. 1. Find the centroid of the region bounded by the curves y = 2x 2 and y = 1 2x 2. Solution. It is obvious, by inspection, that the centroid
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 informationRecognise the Equation of a Circle. Solve Problems about Circles Centred at O. Co-Ordinate Geometry of the Circle - Outcomes
1 Co-Ordinate Geometry of the Circle - Outcomes Recognise the equation of a circle. Solve problems about circles centred at the origin. Solve problems about circles not centred at the origin. Determine
More informationDiffusion Maps, Spectral Clustering and Eigenfunctions of Fokker-Planck Operators
Diffusion Maps, Spectral Clustering and Eigenfunctions of Fokker-Planck Operators Boaz Nadler Stéphane Lafon Ronald R. Coifman Department of Mathematics, Yale University, New Haven, CT 652. {boaz.nadler,stephane.lafon,ronald.coifman}@yale.edu
More informationHeat Kernel and Analysis on Manifolds Excerpt with Exercises. Alexander Grigor yan
Heat Kernel and Analysis on Manifolds Excerpt with Exercises Alexander Grigor yan Department of Mathematics, University of Bielefeld, 33501 Bielefeld, Germany 2000 Mathematics Subject Classification. Primary
More informationMaharashtra State Board Class X Mathematics Geometry Board Paper 2015 Solution. Time: 2 hours Total Marks: 40
Maharashtra State Board Class X Mathematics Geometry Board Paper 05 Solution Time: hours Total Marks: 40 Note:- () Solve all questions. Draw diagrams wherever necessary. ()Use of calculator is not allowed.
More information1 / 23
CBSE-XII-017 EXAMINATION CBSE-X-008 EXAMINATION MATHEMATICS Series: RLH/ Paper & Solution Code: 30//1 Time: 3 Hrs. Max. Marks: 80 General Instuctions : (i) All questions are compulsory. (ii) The question
More informationData dependent operators for the spatial-spectral fusion problem
Data dependent operators for the spatial-spectral fusion problem Wien, December 3, 2012 Joint work with: University of Maryland: J. J. Benedetto, J. A. Dobrosotskaya, T. Doster, K. W. Duke, M. Ehler, A.
More informationBanach Journal of Mathematical Analysis ISSN: (electronic)
Banach J Math Anal (009), no, 64 76 Banach Journal of Mathematical Analysis ISSN: 75-8787 (electronic) http://wwwmath-analysisorg ON A GEOMETRIC PROPERTY OF POSITIVE DEFINITE MATRICES CONE MASATOSHI ITO,
More informationEigenvalues and eigenfunctions of the Laplacian. Andrew Hassell
Eigenvalues and eigenfunctions of the Laplacian Andrew Hassell 1 2 The setting In this talk I will consider the Laplace operator,, on various geometric spaces M. Here, M will be either a bounded Euclidean
More informationEECS 275 Matrix Computation
EECS 275 Matrix Computation Ming-Hsuan Yang Electrical Engineering and Computer Science University of California at Merced Merced, CA 95344 http://faculty.ucmerced.edu/mhyang Lecture 23 1 / 27 Overview
More information(x, y) = d(x, y) = x y.
1 Euclidean geometry 1.1 Euclidean space Our story begins with a geometry which will be familiar to all readers, namely the geometry of Euclidean space. In this first chapter we study the Euclidean distance
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 informationSMT Power Round Solutions : Poles and Polars
SMT Power Round Solutions : Poles and Polars February 18, 011 1 Definition and Basic Properties 1 Note that the unit circles are not necessary in the solutions. They just make the graphs look nicer. (1).0
More informationSection 6. Laplacian, volume and Hessian comparison theorems
Section 6. Laplacian, volume and Hessian comparison theorems Weimin Sheng December 27, 2009 Two fundamental results in Riemannian geometry are the Laplacian and Hessian comparison theorems for the distance
More informationHyperbolic Analytic Geometry
Chapter 6 Hyperbolic Analytic Geometry 6.1 Saccheri Quadrilaterals Recall the results on Saccheri quadrilaterals from Chapter 4. Let S be a convex quadrilateral in which two adjacent angles are right angles.
More informationMinimizing properties of geodesics and convex neighborhoods
Minimizing properties of geodesics and convex neighorhoods Seminar Riemannian Geometry Summer Semester 2015 Prof. Dr. Anna Wienhard, Dr. Gye-Seon Lee Hyukjin Bang July 10, 2015 1. Normal spheres In the
More informationarxiv: v1 [stat.ml] 23 Jul 2008
Data Spectroscopy: Eigenspace of Convolution Operators and Clustering arxiv:87.3719v1 [stat.ml] 23 Jul 28 Tao Shi, Mikhail Belkin and Bin Yu The Ohio State University and University of California, Berkeley
More informationPractice Problems For Test 3
Practice Problems For Test 3 Power Series Preliminary Material. Find the interval of convergence of the following. Be sure to determine the convergence at the endpoints. (a) ( ) k (x ) k (x 3) k= k (b)
More informationMLCC Clustering. Lorenzo Rosasco UNIGE-MIT-IIT
MLCC 2018 - Clustering Lorenzo Rosasco UNIGE-MIT-IIT About this class We will consider an unsupervised setting, and in particular the problem of clustering unlabeled data into coherent groups. MLCC 2018
More informationMATH 829: Introduction to Data Mining and Analysis Clustering II
his lecture is based on U. von Luxburg, A Tutorial on Spectral Clustering, Statistics and Computing, 17 (4), 2007. MATH 829: Introduction to Data Mining and Analysis Clustering II Dominique Guillot Departments
More informationFrom Graphs to Manifolds Weak and Strong Pointwise Consistency of Graph Laplacians
From Graphs to anifolds Weak and Strong Pointwise Consistency of Graph Laplacians atthias Hein 1, Jean-Yves Audibert, and Ulrike von Luxburg 3 1 ax Planck Institute for Biological Cybernetics, Tübingen,
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 informationDraft version September 15, 2015
Novi Sad J. Math. Vol. XX, No. Y, 0ZZ,??-?? ON NEARLY QUASI-EINSTEIN WARPED PRODUCTS 1 Buddhadev Pal and Arindam Bhattacharyya 3 Abstract. We study nearly quasi-einstein warped product manifolds for arbitrary
More informationSpectral Clustering. Guokun Lai 2016/10
Spectral Clustering Guokun Lai 2016/10 1 / 37 Organization Graph Cut Fundamental Limitations of Spectral Clustering Ng 2002 paper (if we have time) 2 / 37 Notation We define a undirected weighted graph
More informationUnsupervised Learning Techniques Class 07, 1 March 2006 Andrea Caponnetto
Unsupervised Learning Techniques 9.520 Class 07, 1 March 2006 Andrea Caponnetto About this class Goal To introduce some methods for unsupervised learning: Gaussian Mixtures, K-Means, ISOMAP, HLLE, Laplacian
More information