Regularizing objective functionals in semi-supervised learning
|
|
- Noah Sharp
- 5 years ago
- Views:
Transcription
1 Regularizing objective functionals in semi-supervised learning Dejan Slepčev Carnegie Mellon University February 9, / 47
2 References S,Thorpe, Analysis of p-laplacian regularization in semi-supervised learning, arxiv Dunlop, S, Stuart, Thorpe, Large-data and zero-noise limits of graph-based semi-supervised learning algorithms in preparation García Trillos, Gerlach, Hein, and S, Error estimates for spectral convergence of the graph Laplacian on random geometric graphs towards the Laplace Beltrami operator, arxiv García Trillos and S, Continuum limit of total variation on point clouds, Arch Ration Mech Anal, 220 no 1, (2016) García Trillos, S, J von Brecht, T Laurent, and X Bresson, Consistency of Cheeger and ratio graph cuts, J Mach Learn Res 17 (2016) 1-46 García Trillos, S, A variational approach to the consistency of spectral clustering, published online Applied and Computational Harmonic Analysis García Trillos and S, On the rate of convergence of empirical measures in -transportation distance, Canad J Math, 67, (2015), pp / 47
3 Semi-supervised learning Colors denote real-valued labels Task: Assign real-valued labels to all of the data points 3 / 47
4 Semi-supervised learning Graph is used to represent the geometry of the data set 4 / 47
5 Semi-supervised learning Consider graph-based objective functions which reward the regularity of the estimator and impose agreement with preassigned labels 5 / 47
6 From point clouds to graphs Let V = {x 1,, x n } be a point cloud in R d : x i W i,j x j Connect nearby vertices: Edge weights W i,j 6 / 47
7 Graph Constructions proximity based graphs W i,j = η(x i x j ) η η L L knn graphs: Connect each vertex with its k nearest neighbors 7 / 47
8 p-dirichelt energy V n = {x 1,, x n }, weight matrix W : W ij := η ( x i x j ) p-dirichlet energy of f n : V n R is E(f n ) = 1 W ij f n (x i ) f n (x j ) p 2 i,j For p = 2 associated operator is the (unnormalized) graph laplacian L = D W, where D = diag(d 1,, d n ) and d i = j W i,j 8 / 47
9 p-laplacian semi-supervised learning Assume we are given k labeled points (x 1, y 1 ), (x k, y k ) and unlabeled points x k+1, x n Question How to label the rest of the points? p-laplacian SSL Minimize subject to constraint E(f n ) = 1 W ij f n (x i ) f n (x j ) p 2 i,j f (x i ) = y i for i = 1,, k Zhu, Ghahramani, and Lafferty 03 introduced the approach with p = 2 Zhou and Schölkopf 05 consider general p 9 / 47
10 p-laplacian semi-supervised learning: Asymptotics p-laplacian SSL Minimize subject to constraint E(f n ) = 1 W ij f n (x i ) f n (x j ) p 2 i,j f (x i ) = y i for i = 1,, k Questions What happens as n? Do minimizers f n converge to a solution of a limiting problem? In what topology should the question be considered? Remark We would like to localize η as n 10 / 47
11 p-laplacian semi-supervised learning: Asymptotics p-laplacian SSL Minimize subject to constraint where E n (f n ) = 1 η ε 2 n 2 ε (x i x j ) f n (x i ) f n (x j ) p f n (x i ) = y i for i = 1,, k i,j η ε ( ) = 1 ( ) ε η d ε Questions Do minimizers f n converge to a solution of the limiting problem? In what topology should the question be considered? How shall ε n scale with n for the convergence to hold? 11 / 47
12 Ground Truth Assumption We assume points x 1, x 2,, are drawn iid out of measure dν = ρdx We also assume ρ is supported on a Lipschitz domain Ω and is bounded above and below by positive constants 12 / 47
13 z Ground Truth Assumption: Manifold version Assume points x 1, x 2,, are drawn iid out of measure dν = ρd Vol M, where M is a compact manifold without boundary, and 0 < ρ < C is continuous x = x, y = -(2 cos(t) (1 - x 2 ) 1/2 (cos(3 x) - 8/5))/5, z = -(2 sin(t) (1 - x 2 ) 1/2 (cos(3 x) - 8/5))/ y x / 47
14 Harmonic semi-supervised learning Nadler, Srebro, and Zhou 09 observed that for p = 2 the minimizers are spiky as n [Also see Wahba 90] Figure: Graph of the minimizer for p = 2, n = 1280, iid data on square; training points (05, 02) with label 0 and (05, 08) with label 1 14 / 47
15 p-laplacian semi-supervised learning El Alaoui, Cheng, Ramdas, Wainwright, and Jordan 16, show that spikes can occur for all p d and propose using p > d Heuristics E (p) n (f ) = 1 ε p n 2 n n η ε (x i x j ) f (x i ) f (x j ) p i,j=1 ε 0 σ η ( ) f (x) f (y p η ε (x i x j ) ρ(x)ρ(y)dxdy ε f (x) p ρ(x) 2 dx Sobolev space W 1,p (Ω) embeds into continuous functions iff p > d 15 / 47
16 Continuum p-laplacian semi-supervised learning µ- measure with density ρ, positive on Ω Continuum p-laplacian SSL Minimize subject to constraints that E (f ) = f (x) p ρ(x) 2 dx Ω f (x i ) = y i for all i = 1,, k The functional is convex The problem has a unique minimizer iff p > d The minimizer lies in W 1,p (Ω) 16 / 47
17 p-laplacian semi-supervised learning Here: d = 1 and p = 15 For ε > 002 the minimizers lack the expected regularity err (15) n (fn) % Graphs Connected fn ε (a) error for p = 15 and d = (b) minimizers for ε = 0023, n = 1280, ten realizations Labeled points are (0, 0) and (1, 1) Ω 17 / 47
18 p-laplacian semi-supervised learning Theorem (Thorpe and S 17) Let p > 1 Let f n be a sequence of minimizers of E (p) n satisfying constraints Let f be a minimizer of E (p) satisfying constraints ( ) 1 (i) If d 3 and n 1 p log n d εn then p > d, f is continuous and n f n converges locally uniformly to f, meaning that for any Ω Ω lim n max f (x k) f n (x k ) = 0 {k n : x k Ω } (ii) If 1 ε n n 1 p then there exists a sequence of real numbers c n such that f n c n converges to zero locally uniformly Note that in case (ii) all information about labels is lost in the limit The discrete minimizers exhibit spikes 18 / 47
19 p-laplacian semi-supervised learning (a) discrete minimizer (b) continuum minimizer Minimizer for p = 4, n = 1280, ε = 0058 iid data on square, with training points (02, 05) and (08, 05) and labels 0 and 1 respectively 19 / 47
20 p-laplacian semi-supervised learning (a) ε = 0058 (b) ε = 009 (c) ε = 02 p = 4 which in 2D is in the well-posed regime 20 / 47
21 Improved p-laplacian semi-supervised learning p > d Labeled points {(x i, y i ) : i = 1,, k} p-laplacian SSL Minimize E n (f n ) = 1 η ε 2 n 2 ε (x i x j ) f n (x i ) f n (x j ) p i,j subject to constraint f n (x m ) = y i whenever x m x i < 2ε, for all i = 1,, k where η ε ( ) = 1 ( ) ε η d ε 21 / 47
22 Asymptotics of improved p-laplacian SSL Theorem (Thorpe and S 17) Let p > d f n be a sequence of minimizers of improved p-laplacian SSL on n-point sample f minimizer of E (p) satisfying constraints Since p > d we know f is continuous ( log n If d 3 and 1 ε n n meaning that for any Ω Ω lim n ) 1 d then f n converges locally uniformly to f, max f (x k) f n (x k ) = 0 {k n : x k Ω } 22 / 47
23 Comparing the original and improved model Here: d = 1, p = 2, and n = 1280 Labeled points are (0, 0) and (1, 1) err (2) n (fn) % Graphs Connected err (2) n (fn) % Graphs Connected ε (a) original model ε (b) improved model Note that the axes on the error plots for the models are not the same 23 / 47
24 Techniques general approach developed with Garcia Trillos (ARMA 16) Γ-convergence Notion and set of techniques of calculus of variations to consider asymptotics of functionals (here random discrete to continuum) TL p space Notion of topology based on optimal transportation which allows to compare functions defined on different spaces (here f n L p (µ n ) and f L p (µ)) We also need Nonlocal operators and their asymptotics In SSL, for constraint to be satisfied we need uniform convergence This also requires discrete regularity and finer compactness results 24 / 47
25 Role of nonlocal operators Heuristics E (p) n (f ) = 1 ε p n 2 n n η ε (x i x j ) f (x i ) f (x j ) p i,j=1 ε 0 σ η ( ) f (x) f (y p η ε (x i x j ) ρ(x)ρ(y)dxdy ε f (x) p ρ(x) 2 dx Discrete problem on graph is closer to a nonlocal functional (with scale ε) than to limiting differential one Nonlocal energy does not have the smoothing properties of the differential one 25 / 47
26 Degeneracy of nonlocal operators Consider Then E (p) n (f ) = 1 ε p n 2 E (p) n (f ) = 2 ε p nn 2 n ε d j=2 n as n, when ε p nn n η ε (x i x j ) f (x i ) f (x j ) p i,j=1 f (x j ) = { 1 if j = 1 0 else ( ) 1 x1 x j η ε n 1 ε p nn 2 nεd n = 1 ε p nn 0 26 / 47
27 PDE based p-laplacian semi-supervised learning Manfredi, Oberman, Sviridov, 2012, Calder 2017 The infinity laplacian is defined by L n f (x i) = max w ij (f (x j ) f (x i )) + min w ij (f (x j ) f (x i )) j j and the p-laplacian is defined by L p nf = 1 d L2 n f + λ(p 2)L f 27 / 47
28 PDE based p-laplacian semi-supervised learning SSL problem L p nf = 1 d L2 n f + λ(p 2)L f L p nf = 0 on Ω \ Ω L f (x i ) = y i for all i = 1,, k Theorem (Calder 17) ( ) 1 log n 3d/2 Assume p > d If d 3 and ε n Then fn converges n uniformly to f, the solution of the limiting problem Note that there is no upper bound on ε n needed 28 / 47
29 Γ-Convergence (Y, d Y ) - metric space, F n : Y [0, ] Definition The sequence {F n } n N Γ-converges ( wrt d Y ) to F : Y [0, ] if: Liminf inequality: For every y Y and whenever y n y lim inf n F n(y n ) F(y), Limsup inequality: For every y Y there exists y n y such that Definition (Compactness property) lim sup F n (y n ) F(y) n {F n } n N satisfies the compactness property if } {y n } n N bounded and = {y {F n (y n )} n N bounded n } n N has convergent subsequence 29 / 47
30 Proposition: Convergence of minimizers Γ-convergence and Compactness imply: If y n is a minimizer of F n and {y n } n N is bounded in Y then along a subsequence y n y as n and y is a minimizer of F In particular, if F has a unique minimizer, then a sequence {y n } n N converges to the unique minimizer of F 30 / 47
31 Topology Consider domain D and V n = {x 1,, x n } random iid points How to compare f n : V n R and u : D R in a way consistent with L 1 topology? Note that u L 1 (ν) and f n L 1 (ν n ), where ν n = 1 n n δ xi i=1 31 / 47
32 Topology Consider domain D and V n = {x 1,, x n } random iid points f n T n f ν n ν Let T n be a transportation map from ν to ν n 32 / 47
33 Topology Let ν be a measure with density ρ, supported on the domain D We need to compare values at nearby points Thus we also penalize transport T n (x) x Metric For u L p (ν) and f n L p (ν n ) d((ν, u), (ν n, f n )) = ( f n (T n (x)) u(x) p + T n (x) x p ) ρ(x)dx inf T n ν=ν n D where T n ν = ν n 33 / 47
34 TL p Space Definition TL p = {(ν, f ) : ν P(D), f L p (ν)} d p TL ((ν, f ), (σ, g)) = y x p + g(y) f (x)) p dπ(x, y) p where inf π Π(ν,σ) D D Π(ν, σ) = {π P(D D) : π(a D) = ν(a), π(d A) = σ(a)} Lemma (TL p, d TL p) is a metric space The topology of TL p agrees with the L p convergence in the sense that (ν, f n ) TLp L (ν, f ) iff f p (ν) n f 34 / 47
35 TL p convergence (ν, f n ) TLp L (ν, f ) iff f p (ν) n f (ν n, f n ) TLp (ν, f ) iff the measures (I f n ) ν n weakly converge to (I f ) ν That is if graphs, considered as measures converge weakly The space TL p is not complete Its completion are the probability measures on the product space D R If (ν n, f n ) TLp (ν, f ) then there exists a sequence of transportation plans ν n such that (1) x y p dπ n (x, y) 0 as n D D We call a sequence of transportation plans π n Π(ν n, ν) stagnating if it satisfies (1) 35 / 47
36 Stagnating sequence: D D x y p dπ n (x, y) 0 TFAE: 1 (ν n, f n ) TLp (ν, f ) as n 2 ν n ν and there exists a stagnating sequence of transportation plans {π n } n N for which (2) D D f (x) f n (y) p dπ n (x, y) 0, as n 3 ν n ν and for every stagnating sequence of transportation plans π n, (2) holds 36 / 47
37 Formally TL p (D) is a fiber bundle over P(D) 37 / 47
38 Γ convergence for p-laplacian Energy E n (f n ) = 1 η ε 2 n 2 ε (x i x j ) f n (x i ) f n (x j ) p Γ-converges in TL p space to σe (f ) = σ f (x) p ρ(x) 2 dx Ω as n provided that i,j 1 ε n log log n n if d = 1 (log n) 3 4 n if d = 2 ( ) 1 log n d n if d 3; 38 / 47
39 Comment of ε n We require (log n)3/4 ε n n 1/2 if d = 2 (log n)1/d ε n n 1/d if d 3 Note that for d 3 this means that typical degree log(n) Does convergence hold if fewer than log(n) neighbors are connected to? 39 / 47
40 Comment of ε n We require (log n)3/4 ε n n 1/2 if d = 2 (log n)1/d ε n n 1/d if d 3 Note that for d 3 this means that typical degree log(n) Does convergence hold if fewer than log(n) neighbors are connected to? No There exists c > 0 such that ε n < c log(n)1/d then with probability n 1/d one the random geometric graph is asymptotically disconnected This implies that for large enough n, min GC n,εn = 0 While inf C > 0 So for d 3 the condition is optimal in terms of scaling 39 / 47
41 Optimal Transportation for p = transportation distance: d (µ, ν) = inf esssup π{ x y : x X, y Y } π Π(µ,ν) If µ = 1 n n i=1 δ x i and ν = 1 n n j=1 δ y j then d (µ, ν) = min max x i y σ(i) σ permutation If µ has density then OT map, T exists (Champion, De Pascale, Juutinen 2008) and d (µ, ν) = T (x) x L (µ) i 40 / 47
42 -OT between a measure and its random sample Optimal matchings in dimension d 3: Ajtai-Komlo s-tusna dy (1983), Yukich and Shor (1991), Garcia Trillos and S (2014) Theorem There are constants c > 0 and C > 0 (depending on d) such that with probability one we can find a sequence of transportation maps {Tn }n N from ν0 to νn (Tn# ν0 = νn ) and such that: c lim inf n n1/d kid Tn k n1/d kid Tn k lim sup C (log n)1/d (log n)1/d n 41 / 47
43 -OT between a measure and its random sample Optimal matchings in dimension d = 2: Leighton and Shor (1986), new proof by Talagrand (2005), Garcia Trillos and S (2014) Theorem There are constants c > 0 and C > 0 such that with probability one we can find a sequence of transportation maps {Tn }n N from ν0 to νn (Tn# ν0 = νn ) and such that: (3) c lim inf n n1/2 kid Tn k n1/2 kid Tn k lim sup C (log n)3/4 (log n)3/4 n 42 / 47
44 Higher order regularizations in SSL with Dunlop, Stuart, and Thorpe, model by Zhou, Belkin 11 Random sample x 1, x n Labels are known if x i Ω L, open Using graph laplacian L n we define A n = (L n + τ 2 I) α Power of a symmetric matrix is defined by M α = PD α P 1 for M = PDP 1 Higher order SSL Minimize subject to constraint E(f ) = 1 2 f n, A n f n µn f n (x i ) = y i whenever x i Ω L 43 / 47
45 Higher order regularizations in SSL Higher order SSL A n = (L n + τ 2 I) α Minimize subject to constraint E(f ) = 1 2 f n, A n f n µn f n (x i ) = y i whenever x i Ω L Theorem (Dunlop, Stuart, S Thorpe) For α > d 2, under usual assumptions, minimizers f n converge in TL 2 to the minimizer of subject to constraint E(f ) = σ u(x)(au)(x)ρ(x)dx Ω u(x i ) = y i whenever x i Ω L where A = (σl c + τi) α and L c u = 1 ρ div(ρ2 u) 44 / 47
46 Higher order regularizations in SSL with Dunlop, Stuart, and Thorpe, model by Zhou, Belkin 11 k labeled points, (x 1, y 1 ), (x k, y k ), and a random sample x k+1, x n Using graph laplacian L n we define A n = (L n + τ 2 I) α Higher order SSL Minimize subject to constraint E(f ) = 1 2 f n, A n f n µn f n (x i ) = y i for i = 1,, k 45 / 47
47 Higher order regularizations Higher order SSL A n = (L n + τ 2 I) α Minimize subject to constraint E(f ) = 1 2 f n, A n f n µn f n (x i ) = y i for i = 1,, k Lemma (Dunlop, Stuart, S Thorpe) If 1 ε n n 1 2α then minimizers fn converge in TL 2 along a subsequence to a constant That is spikes occur 46 / 47
48 Open problems Error estimates In particular why why is the error the smallest for rather coarse graphs Pointwise assigned labels for higher-order operators Better discretization of graphs 47 / 47
CONSISTENCY OF CHEEGER AND RATIO GRAPH CUTS
CONSISTENCY OF CHEEGER AN RATIO GRAPH CUTS NICOLÁS GARCÍA TRILLOS 1, EJAN SLEPČEV 1, JAMES VON BRECHT 2, THOMAS LAURENT 3, XAVIER BRESSON 4. ABSTRACT. This paper establishes the consistency of a family
More informationConsistency of Modularity Clustering on Random Geometric Graphs
Consistency of Modularity Clustering on Random Geometric Graphs Erik Davis The University of Arizona May 10, 2016 Outline Introduction to Modularity Clustering Pointwise Convergence Convergence of Optimal
More informationCONTINUUM LIMIT OF TOTAL VARIATION ON POINT CLOUDS
CONTINUUM LIMIT OF TOTAL VARIATION ON POINT CLOUS NICOLÁS GARCÍA TRILLOS AN EJAN SLEPČEV ABSTRACT. We consider point clouds obtained as random samples of a measure on a Euclidean domain. A graph representing
More informationConsistency of Cheeger and Ratio Graph Cuts
Journal of Machine Learning Research 17 (2016) 1-46 Submitted 11/14; Revised 2/16; Published 10/16 Consistency of Cheeger and Ratio Graph Cuts Nicolás García Trillos ejan Slepčev epartment of Mathematical
More informationGeometric bounds for Steklov eigenvalues
Geometric bounds for Steklov eigenvalues Luigi Provenzano École Polytechnique Fédérale de Lausanne, Switzerland Joint work with Joachim Stubbe June 20, 2017 luigi.provenzano@epfl.ch (EPFL) Steklov eigenvalues
More informationLearning Eigenfunctions: Links with Spectral Clustering and Kernel PCA
Learning Eigenfunctions: Links with Spectral Clustering and Kernel PCA Yoshua Bengio Pascal Vincent Jean-François Paiement University of Montreal April 2, Snowbird Learning 2003 Learning Modal Structures
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 informationRegularization on Discrete Spaces
Regularization on Discrete Spaces Dengyong Zhou and Bernhard Schölkopf Max Planck Institute for Biological Cybernetics Spemannstr. 38, 72076 Tuebingen, Germany {dengyong.zhou, bernhard.schoelkopf}@tuebingen.mpg.de
More informationAN ASYMPTOTIC MEAN VALUE CHARACTERIZATION FOR p-harmonic FUNCTIONS. To the memory of our friend and colleague Fuensanta Andreu
AN ASYMPTOTIC MEAN VALUE CHARACTERIZATION FOR p-harmonic FUNCTIONS JUAN J. MANFREDI, MIKKO PARVIAINEN, AND JULIO D. ROSSI Abstract. We characterize p-harmonic functions in terms of an asymptotic mean value
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 informationDiffuse interface methods on graphs: Data clustering and Gamma-limits
Diffuse interface methods on graphs: Data clustering and Gamma-limits Yves van Gennip joint work with Andrea Bertozzi, Jeff Brantingham, Blake Hunter Department of Mathematics, UCLA Research made possible
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 informationSolution Sheet 3. Solution Consider. with the metric. We also define a subset. and thus for any x, y X 0
Solution Sheet Throughout this sheet denotes a domain of R n with sufficiently smooth boundary. 1. Let 1 p
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 informationAN ASYMPTOTIC MEAN VALUE CHARACTERIZATION FOR p-harmonic FUNCTIONS
AN ASYMPTOTIC MEAN VALUE CHARACTERIZATION FOR p-harmonic FUNCTIONS JUAN J. MANFREDI, MIKKO PARVIAINEN, AND JULIO D. ROSSI Abstract. We characterize p-harmonic functions in terms of an asymptotic mean value
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 informationGeneralized Expanders
Bounded Jerry Kaminker University of California, Davis Lucas Sabalka Binghamton University 28 March, 2009 Outline Bounded 1 2 3 Bounded 4 Bounded Coarse Embeddings Definition (coarse embedding) A family
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 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 informationLecture: Some Statistical Inference Issues (2 of 3)
Stat260/CS294: Spectral Graph Methods Lecture 23-04/16/2015 Lecture: Some Statistical Inference Issues (2 of 3) Lecturer: Michael Mahoney Scribe: Michael Mahoney Warning: these notes are still very rough.
More informationLearning gradients: prescriptive models
Department of Statistical Science Institute for Genome Sciences & Policy Department of Computer Science Duke University May 11, 2007 Relevant papers Learning Coordinate Covariances via Gradients. Sayan
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 informationAppendix to: On the Relation Between Low Density Separation, Spectral Clustering and Graph Cuts
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 hari@cs.uchicago.edu
More informationManifold Coarse Graining for Online Semi-supervised Learning
for Online Semi-supervised Learning Mehrdad Farajtabar, Amirreza Shaban, Hamid R. Rabiee, Mohammad H. Rohban Digital Media Lab, Department of Computer Engineering, Sharif University of Technology, Tehran,
More informationLearning 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 informationLocal contractions and fixed point theorems
Krzysztof Chris Ciesielski 1 and Jakub Jasinski 2 1 West Virginia University Morgantown, WV and University of Pennsylvania Philadelphia, PA 2 University of Scranton, Scranton, PA Real Functions Seminar
More informationTHEOREMS, ETC., FOR MATH 516
THEOREMS, ETC., FOR MATH 516 Results labeled Theorem Ea.b.c (or Proposition Ea.b.c, etc.) refer to Theorem c from section a.b of Evans book (Partial Differential Equations). Proposition 1 (=Proposition
More informationSYMMETRY OF POSITIVE SOLUTIONS OF SOME NONLINEAR EQUATIONS. M. Grossi S. Kesavan F. Pacella M. Ramaswamy. 1. Introduction
Topological Methods in Nonlinear Analysis Journal of the Juliusz Schauder Center Volume 12, 1998, 47 59 SYMMETRY OF POSITIVE SOLUTIONS OF SOME NONLINEAR EQUATIONS M. Grossi S. Kesavan F. Pacella M. Ramaswamy
More informationAnalysis Finite and Infinite Sets The Real Numbers The Cantor Set
Analysis Finite and Infinite Sets Definition. An initial segment is {n N n n 0 }. Definition. A finite set can be put into one-to-one correspondence with an initial segment. The empty set is also considered
More informationGeometric Inference for Probability distributions
Geometric Inference for Probability distributions F. Chazal 1 D. Cohen-Steiner 2 Q. Mérigot 2 1 Geometrica, INRIA Saclay, 2 Geometrica, INRIA Sophia-Antipolis 2009 July 8 F. Chazal, D. Cohen-Steiner, Q.
More information1 Definition of the Riemann integral
MAT337H1, Introduction to Real Analysis: notes on Riemann integration 1 Definition of the Riemann integral Definition 1.1. Let [a, b] R be a closed interval. A partition P of [a, b] is a finite set of
More informationMATHS 730 FC Lecture Notes March 5, Introduction
1 INTRODUCTION MATHS 730 FC Lecture Notes March 5, 2014 1 Introduction Definition. If A, B are sets and there exists a bijection A B, they have the same cardinality, which we write as A, #A. If there exists
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 informationSpaces with Ricci curvature bounded from below
Spaces with Ricci curvature bounded from below Nicola Gigli February 23, 2015 Topics 1) On the definition of spaces with Ricci curvature bounded from below 2) Analytic properties of RCD(K, N) spaces 3)
More informationSusceptible-Infective-Removed Epidemics and Erdős-Rényi random
Susceptible-Infective-Removed Epidemics and Erdős-Rényi random graphs MSR-Inria Joint Centre October 13, 2015 SIR epidemics: the Reed-Frost model Individuals i [n] when infected, attempt to infect all
More informationBoundary value problems for the infinity Laplacian. regularity and geometric results
: regularity and geometric results based on joint works with Graziano Crasta, Roma La Sapienza Calculus of Variations and Its Applications - Lisboa, December 2015 on the occasion of Luísa Mascarenhas 65th
More informationRegularity estimates for fully non linear elliptic equations which are asymptotically convex
Regularity estimates for fully non linear elliptic equations which are asymptotically convex Luis Silvestre and Eduardo V. Teixeira Abstract In this paper we deliver improved C 1,α regularity estimates
More informationOn positive solutions of semi-linear elliptic inequalities on Riemannian manifolds
On positive solutions of semi-linear elliptic inequalities on Riemannian manifolds Alexander Grigor yan University of Bielefeld University of Minnesota, February 2018 Setup and problem statement Let (M,
More informationThe Dirichlet s P rinciple. In this lecture we discuss an alternative formulation of the Dirichlet problem for the Laplace equation:
Oct. 1 The Dirichlet s P rinciple In this lecture we discuss an alternative formulation of the Dirichlet problem for the Laplace equation: 1. Dirichlet s Principle. u = in, u = g on. ( 1 ) If we multiply
More informationcurvature, mixing, and entropic interpolation Simons Feb-2016 and CSE 599s Lecture 13
curvature, mixing, and entropic interpolation Simons Feb-2016 and CSE 599s Lecture 13 James R. Lee University of Washington Joint with Ronen Eldan (Weizmann) and Joseph Lehec (Paris-Dauphine) Markov chain
More informationWeighted Nonlocal Laplacian on Interpolation from Sparse Data
Noname manuscript No. (will be inserted by the editor) Weighted Nonlocal Laplacian on Interpolation from Sparse Data Zuoqiang Shi Stanley Osher Wei Zhu Received: date / Accepted: date Abstract Inspired
More information3 (Due ). Let A X consist of points (x, y) such that either x or y is a rational number. Is A measurable? What is its Lebesgue measure?
MA 645-4A (Real Analysis), Dr. Chernov Homework assignment 1 (Due ). Show that the open disk x 2 + y 2 < 1 is a countable union of planar elementary sets. Show that the closed disk x 2 + y 2 1 is a countable
More informationGeometric 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 informationNonlinear Methods. Data often lies on or near a nonlinear low-dimensional curve aka manifold.
Nonlinear Methods Data often lies on or near a nonlinear low-dimensional curve aka manifold. 27 Laplacian Eigenmaps Linear methods Lower-dimensional linear projection that preserves distances between all
More informationLaplace s Equation. Chapter Mean Value Formulas
Chapter 1 Laplace s Equation Let be an open set in R n. A function u C 2 () is called harmonic in if it satisfies Laplace s equation n (1.1) u := D ii u = 0 in. i=1 A function u C 2 () is called subharmonic
More informationA Remark on -harmonic Functions on Riemannian Manifolds
Electronic Journal of ifferential Equations Vol. 1995(1995), No. 07, pp. 1-10. Published June 15, 1995. ISSN 1072-6691. URL: http://ejde.math.swt.edu or http://ejde.math.unt.edu ftp (login: ftp) 147.26.103.110
More informationProblem 3. Give an example of a sequence of continuous functions on a compact domain converging pointwise but not uniformly to a continuous function
Problem 3. Give an example of a sequence of continuous functions on a compact domain converging pointwise but not uniformly to a continuous function Solution. If we does not need the pointwise limit of
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 informationOn semilinear elliptic equations with measure data
On semilinear elliptic equations with measure data Andrzej Rozkosz (joint work with T. Klimsiak) Nicolaus Copernicus University (Toruń, Poland) Controlled Deterministic and Stochastic Systems Iasi, July
More informationEQUAZIONI A DERIVATE PARZIALI. STEKLOV EIGENVALUES FOR THE -LAPLACIAN
EQUAZIONI A DERIVATE PARZIALI. STEKLOV EIGENVALUES FOR THE -LAPLACIAN J. GARCIA-AZORERO, J. J. MANFREDI, I. PERAL AND J. D. ROSSI Abstract. We study the Steklov eigenvalue problem for the - laplacian.
More informationGeometric Inference for Probability distributions
Geometric Inference for Probability distributions F. Chazal 1 D. Cohen-Steiner 2 Q. Mérigot 2 1 Geometrica, INRIA Saclay, 2 Geometrica, INRIA Sophia-Antipolis 2009 June 1 Motivation What is the (relevant)
More informationSEPARABILITY AND COMPLETENESS FOR THE WASSERSTEIN DISTANCE
SEPARABILITY AND COMPLETENESS FOR THE WASSERSTEIN DISTANCE FRANÇOIS BOLLEY Abstract. In this note we prove in an elementary way that the Wasserstein distances, which play a basic role in optimal transportation
More informationIntroduction and Preliminaries
Chapter 1 Introduction and Preliminaries This chapter serves two purposes. The first purpose is to prepare the readers for the more systematic development in later chapters of methods of real analysis
More informationContents: 1. Minimization. 2. The theorem of Lions-Stampacchia for variational inequalities. 3. Γ -Convergence. 4. Duality mapping.
Minimization Contents: 1. Minimization. 2. The theorem of Lions-Stampacchia for variational inequalities. 3. Γ -Convergence. 4. Duality mapping. 1 Minimization A Topological Result. Let S be a topological
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 informationUnlabeled Data: Now It Helps, Now It Doesn t
institution-logo-filena A. Singh, R. D. Nowak, and X. Zhu. In NIPS, 2008. 1 Courant Institute, NYU April 21, 2015 Outline institution-logo-filena 1 Conflicting Views in Semi-supervised Learning The Cluster
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 informationESTIMATES FOR THE MONGE-AMPERE EQUATION
GLOBAL W 2,p ESTIMATES FOR THE MONGE-AMPERE EQUATION O. SAVIN Abstract. We use a localization property of boundary sections for solutions to the Monge-Ampere equation obtain global W 2,p estimates under
More information1 Math 241A-B Homework Problem List for F2015 and W2016
1 Math 241A-B Homework Problem List for F2015 W2016 1.1 Homework 1. Due Wednesday, October 7, 2015 Notation 1.1 Let U be any set, g be a positive function on U, Y be a normed space. For any f : U Y let
More informationParameter Dependent Quasi-Linear Parabolic Equations
CADERNOS DE MATEMÁTICA 4, 39 33 October (23) ARTIGO NÚMERO SMA#79 Parameter Dependent Quasi-Linear Parabolic Equations Cláudia Buttarello Gentile Departamento de Matemática, Universidade Federal de São
More informationSome aspects of vanishing properties of solutions to nonlinear elliptic equations
RIMS Kôkyûroku, 2014, pp. 1 9 Some aspects of vanishing properties of solutions to nonlinear elliptic equations By Seppo Granlund and Niko Marola Abstract We discuss some aspects of vanishing properties
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 informationCHAPTER 6. Differentiation
CHPTER 6 Differentiation The generalization from elementary calculus of differentiation in measure theory is less obvious than that of integration, and the methods of treating it are somewhat involved.
More informationFORMULATION OF THE LEARNING PROBLEM
FORMULTION OF THE LERNING PROBLEM MIM RGINSKY Now that we have seen an informal statement of the learning problem, as well as acquired some technical tools in the form of concentration inequalities, we
More informationLarge Deviations, Linear Statistics, and Scaling Limits for Mahler Ensemble of Complex Random Polynomials
Large Deviations, Linear Statistics, and Scaling Limits for Mahler Ensemble of Complex Random Polynomials Maxim L. Yattselev joint work with Christopher D. Sinclair International Conference on Approximation
More informationOPTIMAL REGULARITY FOR A TWO-PHASE FREE BOUNDARY PROBLEM RULED BY THE INFINITY LAPLACIAN DAMIÃO J. ARAÚJO, EDUARDO V. TEIXEIRA AND JOSÉ MIGUEL URBANO
Pré-Publicações do Departamento de Matemática Universidade de Coimbra Preprint Number 18 55 OPTIMAL REGULARITY FOR A TWO-PHASE FREE BOUNDARY PROBLEM RULED BY THE INFINITY LAPLACIAN DAMIÃO J. ARAÚJO, EDUARDO
More informationInequalities of Babuška-Aziz and Friedrichs-Velte for differential forms
Inequalities of Babuška-Aziz and Friedrichs-Velte for differential forms Martin Costabel Abstract. For sufficiently smooth bounded plane domains, the equivalence between the inequalities of Babuška Aziz
More informationFunctional Analysis. Franck Sueur Metric spaces Definitions Completeness Compactness Separability...
Functional Analysis Franck Sueur 2018-2019 Contents 1 Metric spaces 1 1.1 Definitions........................................ 1 1.2 Completeness...................................... 3 1.3 Compactness......................................
More informationEverywhere differentiability of infinity harmonic functions
Everywhere differentiability of infinity harmonic functions Lawrence C. Evans and Charles K. Smart Department of Mathematics University of California, Berkeley Abstract We show that an infinity harmonic
More informationOn some weighted fractional porous media equations
On some weighted fractional porous media equations Gabriele Grillo Politecnico di Milano September 16 th, 2015 Anacapri Joint works with M. Muratori and F. Punzo Gabriele Grillo Weighted Fractional PME
More informationOn the uniform Opial property
We consider the noncommutative modular function spaces of measurable operators affiliated with a semifinite von Neumann algebra and show that they are complete with respect to their modular. We prove that
More informationON THE REGULARITY OF SAMPLE PATHS OF SUB-ELLIPTIC DIFFUSIONS ON MANIFOLDS
Bendikov, A. and Saloff-Coste, L. Osaka J. Math. 4 (5), 677 7 ON THE REGULARITY OF SAMPLE PATHS OF SUB-ELLIPTIC DIFFUSIONS ON MANIFOLDS ALEXANDER BENDIKOV and LAURENT SALOFF-COSTE (Received March 4, 4)
More informationEcon Lecture 3. Outline. 1. Metric Spaces and Normed Spaces 2. Convergence of Sequences in Metric Spaces 3. Sequences in R and R n
Econ 204 2011 Lecture 3 Outline 1. Metric Spaces and Normed Spaces 2. Convergence of Sequences in Metric Spaces 3. Sequences in R and R n 1 Metric Spaces and Metrics Generalize distance and length notions
More 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 informationLecture 4 Lebesgue spaces and inequalities
Lecture 4: Lebesgue spaces and inequalities 1 of 10 Course: Theory of Probability I Term: Fall 2013 Instructor: Gordan Zitkovic Lecture 4 Lebesgue spaces and inequalities Lebesgue spaces We have seen how
More information2 (Bonus). Let A X consist of points (x, y) such that either x or y is a rational number. Is A measurable? What is its Lebesgue measure?
MA 645-4A (Real Analysis), Dr. Chernov Homework assignment 1 (Due 9/5). Prove that every countable set A is measurable and µ(a) = 0. 2 (Bonus). Let A consist of points (x, y) such that either x or y is
More information02. Measure and integral. 1. Borel-measurable functions and pointwise limits
(October 3, 2017) 02. Measure and integral Paul Garrett garrett@math.umn.edu http://www.math.umn.edu/ garrett/ [This document is http://www.math.umn.edu/ garrett/m/real/notes 2017-18/02 measure and integral.pdf]
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 informationOn the definition and properties of p-harmonious functions
On the definition and properties of p-harmonious functions University of Pittsburgh, UBA, UAM Workshop on New Connections Between Differential and Random Turn Games, PDE s and Image Processing Pacific
More informationSemi-Supervised Learning in Gigantic Image Collections. Rob Fergus (New York University) Yair Weiss (Hebrew University) Antonio Torralba (MIT)
Semi-Supervised Learning in Gigantic Image Collections Rob Fergus (New York University) Yair Weiss (Hebrew University) Antonio Torralba (MIT) Gigantic Image Collections What does the world look like? High
More informationBounded uniformly continuous functions
Bounded uniformly continuous functions Objectives. To study the basic properties of the C -algebra of the bounded uniformly continuous functions on some metric space. Requirements. Basic concepts of analysis:
More informationAn introduction to Mathematical Theory of Control
An introduction to Mathematical Theory of Control Vasile Staicu University of Aveiro UNICA, May 2018 Vasile Staicu (University of Aveiro) An introduction to Mathematical Theory of Control UNICA, May 2018
More informationInteraction energy between vortices of vector fields on Riemannian surfaces
Interaction energy between vortices of vector fields on Riemannian surfaces Radu Ignat 1 Robert L. Jerrard 2 1 Université Paul Sabatier, Toulouse 2 University of Toronto May 1 2017. Ignat and Jerrard (To(ulouse,ronto)
More informationPROBABILITY: LIMIT THEOREMS II, SPRING HOMEWORK PROBLEMS
PROBABILITY: LIMIT THEOREMS II, SPRING 218. HOMEWORK PROBLEMS PROF. YURI BAKHTIN Instructions. You are allowed to work on solutions in groups, but you are required to write up solutions on your own. Please
More informationDyson series for the PDEs arising in Mathematical Finance I
for the PDEs arising in Mathematical Finance I 1 1 Penn State University Mathematical Finance and Probability Seminar, Rutgers, April 12, 2011 www.math.psu.edu/nistor/ This work was supported in part by
More informationPenalized Barycenters in the Wasserstein space
Penalized Barycenters in the Wasserstein space Elsa Cazelles, joint work with Jérémie Bigot & Nicolas Papadakis Université de Bordeaux & CNRS Journées IOP - Du 5 au 8 Juillet 2017 Bordeaux Elsa Cazelles
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 informationEssential Spectra of complete manifolds
Essential Spectra of complete manifolds Zhiqin Lu Analysis, Complex Geometry, and Mathematical Physics: A Conference in Honor of Duong H. Phong May 7, 2013 Zhiqin Lu, Dept. Math, UCI Essential Spectra
More information215 Problem 1. (a) Define the total variation distance µ ν tv for probability distributions µ, ν on a finite set S. Show that
15 Problem 1. (a) Define the total variation distance µ ν tv for probability distributions µ, ν on a finite set S. Show that µ ν tv = (1/) x S µ(x) ν(x) = x S(µ(x) ν(x)) + where a + = max(a, 0). Show that
More informationRIEMANNIAN GEOMETRY COMPACT METRIC SPACES. Jean BELLISSARD 1. Collaboration:
RIEMANNIAN GEOMETRY of COMPACT METRIC SPACES Jean BELLISSARD 1 Georgia Institute of Technology, Atlanta School of Mathematics & School of Physics Collaboration: I. PALMER (Georgia Tech, Atlanta) 1 e-mail:
More informationREGULARITY OF THE OPTIMAL SETS FOR SOME SPECTRAL FUNCTIONALS
REGULARITY OF THE OPTIMAL SETS FOR SOME SPECTRAL FUNCTIONALS DARIO MAZZOLENI, SUSANNA TERRACINI, BOZHIDAR VELICHKOV Abstract. In this paper we study the regularity of the optimal sets for the shape optimization
More informationModel 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 informationPDEs in Image Processing, Tutorials
PDEs in Image Processing, Tutorials Markus Grasmair Vienna, Winter Term 2010 2011 Direct Methods Let X be a topological space and R: X R {+ } some functional. following definitions: The mapping R is lower
More informationOPTIMAL POTENTIALS FOR SCHRÖDINGER OPERATORS. 1. Introduction In this paper we consider optimization problems of the form. min F (V ) : V V, (1.
OPTIMAL POTENTIALS FOR SCHRÖDINGER OPERATORS G. BUTTAZZO, A. GEROLIN, B. RUFFINI, AND B. VELICHKOV Abstract. We consider the Schrödinger operator + V (x) on H 0 (), where is a given domain of R d. Our
More informationMaths 212: Homework Solutions
Maths 212: Homework Solutions 1. The definition of A ensures that x π for all x A, so π is an upper bound of A. To show it is the least upper bound, suppose x < π and consider two cases. If x < 1, then
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 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 informationGraphs, 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 informationNote on the Chen-Lin Result with the Li-Zhang Method
J. Math. Sci. Univ. Tokyo 18 (2011), 429 439. Note on the Chen-Lin Result with the Li-Zhang Method By Samy Skander Bahoura Abstract. We give a new proof of the Chen-Lin result with the method of moving
More informationBlow-up Analysis of a Fractional Liouville Equation in dimension 1. Francesca Da Lio
Blow-up Analysis of a Fractional Liouville Equation in dimension 1 Francesca Da Lio Outline Liouville Equation: Local Case Geometric Motivation Brezis & Merle Result Nonlocal Framework The Half-Laplacian
More information