UNSUPERVISED CLUSTERING WITH MST: APPLICATION TO ASTEROID DATA Mai 2005 O. Michel, P.Bendjoya,

Size: px
Start display at page:

Download "UNSUPERVISED CLUSTERING WITH MST: APPLICATION TO ASTEROID DATA Mai 2005 O. Michel, P.Bendjoya,"

Transcription

1 UNSUPERVISED CLUSTERING WITH MST: APPLICATION TO ASTEROID DATA Mai 25 O. Michel, P.Bendjoya,

2 Classification...a certain knowhow (a,e,i)computation Proposed metrics(zappala et al., 99) d(i, j) = where mm ˆ ij â ij 5 4 (a i a j ) â ij 2 + 2(e i e j )2 + 2(i i i j )2 ms ˆ mm ij = (mm i +mm j )/2, â ij = (a i +a j )/2, mma 3 = cste(kepler) 2

3 FoA detection methods Notice that : No supervised approach is possible Many objects that are NOT belonging to a family may have close (a, e, i) params : interlopers, outliers {(a, e, i) + d} is NOT an Euclidean space. Existing satisfactory approaches : Hierarchical Clustering Method (Zappala et al, 99,95) Wavelet based over-densities detection (Bendjoya et al, 993,97) BUT : both imply heavy computational burden BUT : both require ad-hoc parameter or threshold definitions 3

4 New needs About. asteroids 4

5 MST : définition Soit X = {x,..., x n } une réalisation de n vecteurs aléatoires i.i.d., où chaque x i IR d suit une distribution P, de densité de Lebesgue λ. Les x i sont considérés comme les sommets d un graphe acyclique totalement connecté (T n ), de segments e i,j et de longueur : L γ (T n ) := e i,j T n e i,j γ, γ ], d[ Par définition le graphe de représentation minimal ou Minimal Spanning Tree (MST) est, parmi l ensemble des graphes, celui de longueur minimale : T n := arg min T n L γ (T n ) Algorithme de calcul de solution exacte de complexité O(n log n). 5

6 A random set of n = 28 realizations from 2D separable uniform density over [, ] 2, and the MST spanning these points 28 random samples MST z 2 z z z 6

7 Applications in MST : Motivations Image indexing Content based retrievial Registration Target detection Robust entropy and divergence estimation Mutual information between data flows... 7

8 Entropic Spanning Graphs for α = (d γ) d, and γ d : L(Z n ) = min e T e e γ Ĥ α (Z n ) = [ ln L(Zn )/n α ] ln β L,γ α Renyi s Entropy 8

9 Back to FoA detection : Alternative graph (MST) based approach Motivations: a performances MST and k-mst for unsupervised clustering (Hero et al 99,2) b relation of MST length to Rényi entropy of the underlying distribution (Hero et al, 98) c relation of MST based single linkage clustering with entropy clustering (Michel 2) d exploitation of Prim s algorithm for MST construction to detect clusters (Olman 4) e existence of O(n log n) implementations of Prim s MST construction HOWEVER, points (b) and (c) requires that an Euclidean metrics is used : 9

10 Alternate metrics, from dimensional analysis x = 2. e a y = 2. z = sin i a 54 a d 2 e (i, j) = (x i x j ) 2 + (y i y j ) 2 + (z i z j ) 2 rk: as for our data, a > 2 units, no singularity is introduced. rk2: this transform amounts to squeeze and stretch the (a, e, i) space, such that euclidean distances apply.

11 Exploiting Prim s algorithm Summary of the Prim s algorithm (NN accretion method) : Initialize with an arbitrary T. let T m be a partial m vertices MST, issued by m iterations; iteration m : - among the unconnected vertices, connect the closest to T m, making T m+ - Iterate until no unconnected vertex is left. Olman s idea : record l(m), the length of the edge built to connect a new vertex at iteration m

12 Ex. of application on simulation data, 6 s= edge length agregation s= index 6 z=inc.5. edge length y=exc x=dga edge length agregation s=2 index agregation index.3 xoy.3 xoz coded data, s= coded data, s= yz coded data, s=

13 Ex. of application on simulation data, 2 data, in (a,e,i) coordinates extracted clusters 5 4 edge length accretion index z=i.2 z=i y=e x=a y=e x=a rk: For both examples, threshold was determined by η = αstd ({ e i }, i =,..., n) with α = here 3

14 COR Proba de detection Proba de Fausse alarme 4

15 Pd (a) family (2), interlopers; tests d25v5,3,6 (b) (c) (a) : d25v5 (b) : d25v3 (c) : d25v6 o : MST clustering * : WVT clustering Pfa Clust : ROC for simulation files containing one unique family of 25 asteroid, created from an initial impact of parameters 5, 3, 6, respectively. ROCs for WT based and MST based approaches. Initial metrics d. Pd families (,5), interlopers; test d25.5v2.5, d25.5v5.5 (a) (b) (a) : d25.5v5.5 (b) : d25.5v2.5 o : MST clustering * : WVT clustering Pfa 2Clust: ROC for simulation files containing two families of asteroid (25 and 5) or (25 and 5) objects, created from initial impacts of parameters respectively (2 and 5) or (5 and 5) respectively. ROCs for WT based and MST based approaches. Initial metrics d. 5

16 Pd Pd family (2), interlopers; tests d25v5,3, Pfa, Euclidean norm families (,5), interlopers; test d25.5v2.5, d25.5v5.5 diamond : MST clustering * : WVT clustering Pfa Euclidean norm Clust : ROC for simulation files containing one unique family of 25 asteroid, created from an initial impact of parameters 5, 3, 6, respectively. ROCs for WT based using d and MST Euclidean metrics d e based approaches 2Clust: ROC for simulation files containing two families of asteroid (25 and 5) or (25 and 5) objects, created from initial impacts of parameters respectively (2 and 5) or (5 and 5) respectively. ROCs for WT based using d and MST Euclidean metrics d e based approaches. 6

17 Setting the threshold, Empirical approach : Let < α < ; for fixed α, measure N c =Nb of detected significant clusters Record N c = f(α) Nb of detected cluster(s) Number of cluster with more than objects Estimate α opt = max(α) for largest the plateau in f(α) α 7

18 Setting the threshold, 2 Entropy based approach : Let < α < ; for fixed α, H in, H out for MST length of detected significant clusters Record H in H out = f(α) arbitrary units Clusters Entropy - Background Entropy, exp.scale Estimate α opt at the most important step α 8

19 Conclusion tools exist no matter the space dimension an entropic justication of the segmentation to your convenience... Thank you 9

Estimation of Rényi Information Divergence via Pruned Minimal Spanning Trees 1

Estimation of Rényi Information Divergence via Pruned Minimal Spanning Trees 1 Estimation of Rényi Information Divergence via Pruned Minimal Spanning Trees Alfred Hero Dept. of EECS, The university of Michigan, Ann Arbor, MI 489-, USA Email: hero@eecs.umich.edu Olivier J.J. Michel

More information

Entropic Graphs. Alfred O. Hero. Dept. EECS, Dept Biomed. Eng., Dept. Statistics University of Michigan - Ann Arbor

Entropic Graphs. Alfred O. Hero. Dept. EECS, Dept Biomed. Eng., Dept. Statistics University of Michigan - Ann Arbor Entropic Graphs Alfred O. Hero Dept. EECS, Dept Biomed. Eng., Dept. Statistics University of Michigan - Ann Arbor hero@eecs.umich.edu http://www.eecs.umich.edu/ hero Collaborators: H. Heemuchwala, J. Costa,

More information

Renyi divergence and asymptotic theory of minimal K-point random graphs Alfred Hero Dept. of EECS, The University of Michigan, Summer 1999

Renyi divergence and asymptotic theory of minimal K-point random graphs Alfred Hero Dept. of EECS, The University of Michigan, Summer 1999 Renyi divergence and asymptotic theory of minimal K-point random graphs Alfred Hero Dept. of EECS, The University of Michigan, Summer 999 Outline Rényi Entropy and Rényi Divergence ffl Euclidean k-minimal

More information

University of Florida CISE department Gator Engineering. Clustering Part 1

University of Florida CISE department Gator Engineering. Clustering Part 1 Clustering Part 1 Dr. Sanjay Ranka Professor Computer and Information Science and Engineering University of Florida, Gainesville What is Cluster Analysis? Finding groups of objects such that the objects

More information

Entropic Graphs. Alfred O. Hero. Dept. EECS, Dept Biomed. Eng., Dept. Statistics University of Michigan - Ann Arbor

Entropic Graphs. Alfred O. Hero. Dept. EECS, Dept Biomed. Eng., Dept. Statistics University of Michigan - Ann Arbor Entropic Graphs Alfred O Hero Dept EECS, Dept Biomed Eng, Dept Statistics University of Michigan - Ann Arbor hero@eecsumichedu http://wwweecsumichedu/ hero Collaborators: A Almal, J Costa, H Neemuchwala,

More information

EBEM: An Entropy-based EM Algorithm for Gaussian Mixture Models

EBEM: An Entropy-based EM Algorithm for Gaussian Mixture Models EBEM: An Entropy-based EM Algorithm for Gaussian Mixture Models Antonio Peñalver Benavent, Francisco Escolano Ruiz and Juan M. Sáez Martínez Robot Vision Group Alicante University 03690 Alicante, Spain

More information

Large Scale Environment Partitioning in Mobile Robotics Recognition Tasks

Large Scale Environment Partitioning in Mobile Robotics Recognition Tasks Large Scale Environment in Mobile Robotics Recognition Tasks Boyan Bonev, Miguel Cazorla {boyan,miguel}@dccia.ua.es Robot Vision Group Department of Computer Science and Artificial Intelligence University

More information

Cluster Analysis (Sect. 9.6/Chap. 14 of Wilks) Notes by Hong Li

Cluster Analysis (Sect. 9.6/Chap. 14 of Wilks) Notes by Hong Li 77 Cluster Analysis (Sect. 9.6/Chap. 14 of Wilks) Notes by Hong Li 1) Introduction Cluster analysis deals with separating data into groups whose identities are not known in advance. In general, even the

More information

Geometric entropy minimization (GEM) for anomaly detection and localization

Geometric entropy minimization (GEM) for anomaly detection and localization Geometric entropy minimization (GEM) for anomaly detection and localization Alfred O Hero, III University of Michigan Ann Arbor, MI 89- hero@umich.edu Abstract We introduce a novel adaptive non-parametric

More information

Principles of Pattern Recognition. C. A. Murthy Machine Intelligence Unit Indian Statistical Institute Kolkata

Principles of Pattern Recognition. C. A. Murthy Machine Intelligence Unit Indian Statistical Institute Kolkata Principles of Pattern Recognition C. A. Murthy Machine Intelligence Unit Indian Statistical Institute Kolkata e-mail: murthy@isical.ac.in Pattern Recognition Measurement Space > Feature Space >Decision

More information

Computer Vision Group Prof. Daniel Cremers. 14. Clustering

Computer Vision Group Prof. Daniel Cremers. 14. Clustering Group Prof. Daniel Cremers 14. Clustering Motivation Supervised learning is good for interaction with humans, but labels from a supervisor are hard to obtain Clustering is unsupervised learning, i.e. it

More information

REGO: Rank-based Estimation of Rényi Information using Euclidean Graph Optimization

REGO: Rank-based Estimation of Rényi Information using Euclidean Graph Optimization REGO: Rank-based Estimation of Rényi Information using Euclidean Graph Optimization Barnabás Póczos Sergey Kirshner Csaba Szepesvári Dept. of Computing Science University of Alberta Edmonton, AB Canada,

More information

Combinatorial Optimization

Combinatorial Optimization Combinatorial Optimization Problem set 8: solutions 1. Fix constants a R and b > 1. For n N, let f(n) = n a and g(n) = b n. Prove that f(n) = o ( g(n) ). Solution. First we observe that g(n) 0 for all

More information

Network models: random graphs

Network models: random graphs Network models: random graphs Leonid E. Zhukov School of Data Analysis and Artificial Intelligence Department of Computer Science National Research University Higher School of Economics Structural Analysis

More information

Research Overview. Kristjan Greenewald. February 2, University of Michigan - Ann Arbor

Research Overview. Kristjan Greenewald. February 2, University of Michigan - Ann Arbor Research Overview Kristjan Greenewald University of Michigan - Ann Arbor February 2, 2016 2/17 Background and Motivation Want efficient statistical modeling of high-dimensional spatio-temporal data with

More information

Final Exam, Machine Learning, Spring 2009

Final Exam, Machine Learning, Spring 2009 Name: Andrew ID: Final Exam, 10701 Machine Learning, Spring 2009 - The exam is open-book, open-notes, no electronics other than calculators. - The maximum possible score on this exam is 100. You have 3

More information

Applications of Information Geometry to Hypothesis Testing and Signal Detection

Applications of Information Geometry to Hypothesis Testing and Signal Detection CMCAA 2016 Applications of Information Geometry to Hypothesis Testing and Signal Detection Yongqiang Cheng National University of Defense Technology July 2016 Outline 1. Principles of Information Geometry

More information

Clustering. CSL465/603 - Fall 2016 Narayanan C Krishnan

Clustering. CSL465/603 - Fall 2016 Narayanan C Krishnan Clustering CSL465/603 - Fall 2016 Narayanan C Krishnan ckn@iitrpr.ac.in Supervised vs Unsupervised Learning Supervised learning Given x ", y " "%& ', learn a function f: X Y Categorical output classification

More information

Information Theory in Computer Vision and Pattern Recognition

Information Theory in Computer Vision and Pattern Recognition Francisco Escolano Pablo Suau Boyan Bonev Information Theory in Computer Vision and Pattern Recognition Foreword by Alan Yuille ~ Springer Contents 1 Introduction...............................................

More information

Navigation on a Poisson point process. Nicolas Bonichon Jean-François Marckert (LaBRI - Bordeaux):

Navigation on a Poisson point process. Nicolas Bonichon Jean-François Marckert (LaBRI - Bordeaux): Navigation on a Poisson point process Nicolas Bonichon Jean-François Marckert (LaBRI - Bordeaux): http://www.labri.fr/perso/name Luminy, 2011 Motivations... Notion of spanner Let G be a graph with some

More information

Lab 12: Structured Prediction

Lab 12: Structured Prediction December 4, 2014 Lecture plan structured perceptron application: confused messages application: dependency parsing structured SVM Class review: from modelization to classification What does learning mean?

More information

Notes on MapReduce Algorithms

Notes on MapReduce Algorithms Notes on MapReduce Algorithms Barna Saha 1 Finding Minimum Spanning Tree of a Dense Graph in MapReduce We are given a graph G = (V, E) on V = N vertices and E = m N 1+c edges for some constant c > 0. Our

More information

Entropic-graphs: Applications

Entropic-graphs: Applications Entropic-graphs: Applications Alfred O. Hero Dept. EECS, Dept Biomed. Eng., Dept. Statistics University of Michigan - Ann Arbor hero@eecs.umich.edu http://www.eecs.umich.edu/ hero Collaborators: Huzefa

More information

Probabilistic & Unsupervised Learning

Probabilistic & Unsupervised Learning Probabilistic & Unsupervised Learning Week 2: Latent Variable Models Maneesh Sahani maneesh@gatsby.ucl.ac.uk Gatsby Computational Neuroscience Unit, and MSc ML/CSML, Dept Computer Science University College

More information

Robust Laplacian Eigenmaps Using Global Information

Robust Laplacian Eigenmaps Using Global Information Manifold Learning and its Applications: Papers from the AAAI Fall Symposium (FS-9-) Robust Laplacian Eigenmaps Using Global Information Shounak Roychowdhury ECE University of Texas at Austin, Austin, TX

More information

Unsupervised Learning Techniques Class 07, 1 March 2006 Andrea Caponnetto

Unsupervised 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

Clustering using Mixture Models

Clustering using Mixture Models Clustering using Mixture Models The full posterior of the Gaussian Mixture Model is p(x, Z, µ,, ) =p(x Z, µ, )p(z )p( )p(µ, ) data likelihood (Gaussian) correspondence prob. (Multinomial) mixture prior

More information

1 Mechanistic and generative models of network structure

1 Mechanistic and generative models of network structure 1 Mechanistic and generative models of network structure There are many models of network structure, and these largely can be divided into two classes: mechanistic models and generative or probabilistic

More information

Adaptive Multi-Modal Sensing of General Concealed Targets

Adaptive Multi-Modal Sensing of General Concealed Targets Adaptive Multi-Modal Sensing of General Concealed argets Lawrence Carin Balaji Krishnapuram, David Williams, Xuejun Liao and Ya Xue Department of Electrical & Computer Engineering Duke University Durham,

More information

Computational Linear Algebra

Computational Linear Algebra Computational Linear Algebra PD Dr. rer. nat. habil. Ralf Peter Mundani Computation in Engineering / BGU Scientific Computing in Computer Science / INF Winter Term 2017/18 Part 3: Iterative Methods PD

More information

Data Preprocessing. Cluster Similarity

Data Preprocessing. Cluster Similarity 1 Cluster Similarity Similarity is most often measured with the help of a distance function. The smaller the distance, the more similar the data objects (points). A function d: M M R is a distance on M

More information

More on Unsupervised Learning

More on Unsupervised Learning More on Unsupervised Learning Two types of problems are to find association rules for occurrences in common in observations (market basket analysis), and finding the groups of values of observational data

More information

Plug-in Measure-Transformed Quasi Likelihood Ratio Test for Random Signal Detection

Plug-in Measure-Transformed Quasi Likelihood Ratio Test for Random Signal Detection Plug-in Measure-Transformed Quasi Likelihood Ratio Test for Random Signal Detection Nir Halay and Koby Todros Dept. of ECE, Ben-Gurion University of the Negev, Beer-Sheva, Israel February 13, 2017 1 /

More information

When Dictionary Learning Meets Classification

When Dictionary Learning Meets Classification When Dictionary Learning Meets Classification Bufford, Teresa 1 Chen, Yuxin 2 Horning, Mitchell 3 Shee, Liberty 1 Mentor: Professor Yohann Tendero 1 UCLA 2 Dalhousie University 3 Harvey Mudd College August

More information

Vers un apprentissage subquadratique pour les mélanges d arbres

Vers un apprentissage subquadratique pour les mélanges d arbres Vers un apprentissage subquadratique pour les mélanges d arbres F. Schnitzler 1 P. Leray 2 L. Wehenkel 1 fschnitzler@ulg.ac.be 1 Université deliège 2 Université de Nantes 10 mai 2010 F. Schnitzler (ULG)

More information

Compressing Tabular Data via Pairwise Dependencies

Compressing Tabular Data via Pairwise Dependencies Compressing Tabular Data via Pairwise Dependencies Amir Ingber, Yahoo! Research TCE Conference, June 22, 2017 Joint work with Dmitri Pavlichin, Tsachy Weissman (Stanford) Huge datasets: everywhere - Internet

More information

Clustering, K-Means, EM Tutorial

Clustering, K-Means, EM Tutorial Clustering, K-Means, EM Tutorial Kamyar Ghasemipour Parts taken from Shikhar Sharma, Wenjie Luo, and Boris Ivanovic s tutorial slides, as well as lecture notes Organization: Clustering Motivation K-Means

More information

Community Detection on Euclidean Random Graphs

Community Detection on Euclidean Random Graphs Community Detection on Euclidean Random Graphs Abishek Sankararaman, François Baccelli July 3, 207 Abstract Motivated by applications in online social networks, we introduce and study the problem of Community

More information

Computer Vision Group Prof. Daniel Cremers. 6. Mixture Models and Expectation-Maximization

Computer Vision Group Prof. Daniel Cremers. 6. Mixture Models and Expectation-Maximization Prof. Daniel Cremers 6. Mixture Models and Expectation-Maximization Motivation Often the introduction of latent (unobserved) random variables into a model can help to express complex (marginal) distributions

More information

which arises when we compute the orthogonal projection of a vector y in a subspace with an orthogonal basis. Hence assume that P y = A ij = x j, x i

which arises when we compute the orthogonal projection of a vector y in a subspace with an orthogonal basis. Hence assume that P y = A ij = x j, x i MODULE 6 Topics: Gram-Schmidt orthogonalization process We begin by observing that if the vectors {x j } N are mutually orthogonal in an inner product space V then they are necessarily linearly independent.

More information

2 A Model, Harmonic Map, Problem

2 A Model, Harmonic Map, Problem ELLIPTIC SYSTEMS JOHN E. HUTCHINSON Department of Mathematics School of Mathematical Sciences, A.N.U. 1 Introduction Elliptic equations model the behaviour of scalar quantities u, such as temperature or

More information

Link Prediction. Eman Badr Mohammed Saquib Akmal Khan

Link Prediction. Eman Badr Mohammed Saquib Akmal Khan Link Prediction Eman Badr Mohammed Saquib Akmal Khan 11-06-2013 Link Prediction Which pair of nodes should be connected? Applications Facebook friend suggestion Recommendation systems Monitoring and controlling

More information

Géza Ódor, MTA-EK-MFA Budapest Ronald Dickman, UFMG Brazil 08/04/2015

Géza Ódor, MTA-EK-MFA Budapest Ronald Dickman, UFMG Brazil 08/04/2015 Localization, Griffiths phases and burstyness in neural network models Géza Ódor, MTA-EK-MFA Budapest Ronald Dickman, UFMG Brazil 08/04/2015 Partners: Gergely Ódor R. Juhász Infocommunication technologies

More information

Clustering K-means. Machine Learning CSE546. Sham Kakade University of Washington. November 15, Review: PCA Start: unsupervised learning

Clustering K-means. Machine Learning CSE546. Sham Kakade University of Washington. November 15, Review: PCA Start: unsupervised learning Clustering K-means Machine Learning CSE546 Sham Kakade University of Washington November 15, 2016 1 Announcements: Project Milestones due date passed. HW3 due on Monday It ll be collaborative HW2 grades

More information

Clustering. Genome 373 Genomic Informatics Elhanan Borenstein. Some slides adapted from Jacques van Helden

Clustering. Genome 373 Genomic Informatics Elhanan Borenstein. Some slides adapted from Jacques van Helden Clustering Genome 373 Genomic Informatics Elhanan Borenstein Some slides adapted from Jacques van Helden The clustering problem The goal of gene clustering process is to partition the genes into distinct

More information

Network models: dynamical growth and small world

Network models: dynamical growth and small world Network models: dynamical growth and small world Leonid E. Zhukov School of Data Analysis and Artificial Intelligence Department of Computer Science National Research University Higher School of Economics

More information

Clustering. Genome 559: Introduction to Statistical and Computational Genomics Elhanan Borenstein. Some slides adapted from Jacques van Helden

Clustering. Genome 559: Introduction to Statistical and Computational Genomics Elhanan Borenstein. Some slides adapted from Jacques van Helden Clustering Genome 559: Introduction to Statistical and Computational Genomics Elhanan Borenstein Some slides adapted from Jacques van Helden Gene expression profiling A quick review Which molecular processes/functions

More information

VoI for Learning and Inference! in Sensor Networks!

VoI for Learning and Inference! in Sensor Networks! ARO MURI on Value-centered Information Theory for Adaptive Learning, Inference, Tracking, and Exploitation VoI for Learning and Inference in Sensor Networks Gene Whipps 1,2, Emre Ertin 2, Randy Moses 2

More information

Lecture 4. 1 Estimating the number of connected components and minimum spanning tree

Lecture 4. 1 Estimating the number of connected components and minimum spanning tree CS 59000 CTT Current Topics in Theoretical CS Aug 30, 2012 Lecturer: Elena Grigorescu Lecture 4 Scribe: Pinar Yanardag Delul 1 Estimating the number of connected components and minimum spanning tree In

More information

Information Measure Estimation and Applications: Boosting the Effective Sample Size from n to n ln n

Information Measure Estimation and Applications: Boosting the Effective Sample Size from n to n ln n Information Measure Estimation and Applications: Boosting the Effective Sample Size from n to n ln n Jiantao Jiao (Stanford EE) Joint work with: Kartik Venkat Yanjun Han Tsachy Weissman Stanford EE Tsinghua

More information

Computational Linear Algebra

Computational Linear Algebra Computational Linear Algebra PD Dr. rer. nat. habil. Ralf-Peter Mundani Computation in Engineering / BGU Scientific Computing in Computer Science / INF Winter Term 2018/19 Part 4: Iterative Methods PD

More information

A stretched-exponential Pinning Model with heavy-tailed Disorder

A stretched-exponential Pinning Model with heavy-tailed Disorder A stretched-exponential Pinning Model with heavy-tailed Disorder Niccolò Torri Université Claude-Bernard - Lyon 1 & Università degli Studi di Milano-Bicocca Roma, October 8, 2014 References A. Auffinger

More information

Computational Linear Algebra

Computational Linear Algebra Computational Linear Algebra PD Dr. rer. nat. habil. Ralf Peter Mundani Computation in Engineering / BGU Scientific Computing in Computer Science / INF Winter Term 2017/18 Part 3: Iterative Methods PD

More information

CS249: ADVANCED DATA MINING

CS249: ADVANCED DATA MINING CS249: ADVANCED DATA MINING Clustering Evaluation and Practical Issues Instructor: Yizhou Sun yzsun@cs.ucla.edu May 2, 2017 Announcements Homework 2 due later today Due May 3 rd (11:59pm) Course project

More information

JOURNAL OF PHYSICAL AGENTS, VOL. 4, NO. 2, MAY Large Scale Environment Partitioning in Mobile Robotics Recognition Tasks

JOURNAL OF PHYSICAL AGENTS, VOL. 4, NO. 2, MAY Large Scale Environment Partitioning in Mobile Robotics Recognition Tasks JOURNAL OF PHYSICAL AGENTS, VOL. 4, NO., MAY Large Scale Environment Partitioning in Mobile Robotics Recognition Tasks Boyan Bonev and Miguel Cazorla Abstract In this paper we present a scalable machine

More information

On the Optimality of the Greedy Heuristic in Wavelet Synopses for Range Queries

On the Optimality of the Greedy Heuristic in Wavelet Synopses for Range Queries On the Optimality of the Greedy Heuristic in Wavelet Synopses for Range Queries Yossi Matias School of Computer Science Tel Aviv University Tel Aviv 69978, Israel matias@tau.ac.il Daniel Urieli School

More information

Introduction to Statistical Inference

Introduction to Statistical Inference Structural Health Monitoring Using Statistical Pattern Recognition Introduction to Statistical Inference Presented by Charles R. Farrar, Ph.D., P.E. Outline Introduce statistical decision making for Structural

More information

Dynamic Approaches: The Hidden Markov Model

Dynamic Approaches: The Hidden Markov Model Dynamic Approaches: The Hidden Markov Model Davide Bacciu Dipartimento di Informatica Università di Pisa bacciu@di.unipi.it Machine Learning: Neural Networks and Advanced Models (AA2) Inference as Message

More information

Dreem Challenge report (team Bussanati)

Dreem Challenge report (team Bussanati) Wavelet course, MVA 04-05 Simon Bussy, simon.bussy@gmail.com Antoine Recanati, arecanat@ens-cachan.fr Dreem Challenge report (team Bussanati) Description and specifics of the challenge We worked on the

More information

Clustering. Genome 559: Introduction to Statistical and Computational Genomics Elhanan Borenstein. Some slides adapted from Jacques van Helden

Clustering. Genome 559: Introduction to Statistical and Computational Genomics Elhanan Borenstein. Some slides adapted from Jacques van Helden Clustering Genome 559: Introduction to Statistical and Computational Genomics Elhanan Borenstein Some slides adapted from Jacques van Helden Gene expression profiling A quick review Which molecular processes/functions

More information

Learning Objectives for Stat 225

Learning Objectives for Stat 225 Learning Objectives for Stat 225 08/20/12 Introduction to Probability: Get some general ideas about probability, and learn how to use sample space to compute the probability of a specific event. Set Theory:

More information

Global vs. Multiscale Approaches

Global 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 information

Bipartite k-nearest neighbor graphs, entropy, and learning

Bipartite k-nearest neighbor graphs, entropy, and learning Bipartite k-nearest neighbor graphs, entropy, and learning Alfred Hero University of Michigan - Ann Arbor June 14, 2012 1 / 71 1 Motivation 2 knn constructs 3 Bipartite knn 4 Ensemble weighted BP-kNN estimators

More information

Sparsity Models. Tong Zhang. Rutgers University. T. Zhang (Rutgers) Sparsity Models 1 / 28

Sparsity Models. Tong Zhang. Rutgers University. T. Zhang (Rutgers) Sparsity Models 1 / 28 Sparsity Models Tong Zhang Rutgers University T. Zhang (Rutgers) Sparsity Models 1 / 28 Topics Standard sparse regression model algorithms: convex relaxation and greedy algorithm sparse recovery analysis:

More information

9 Classification. 9.1 Linear Classifiers

9 Classification. 9.1 Linear Classifiers 9 Classification This topic returns to prediction. Unlike linear regression where we were predicting a numeric value, in this case we are predicting a class: winner or loser, yes or no, rich or poor, positive

More information

Manifold Coarse Graining for Online Semi-supervised Learning

Manifold 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 information

15 Singular Value Decomposition

15 Singular Value Decomposition 15 Singular Value Decomposition For any high-dimensional data analysis, one s first thought should often be: can I use an SVD? The singular value decomposition is an invaluable analysis tool for dealing

More information

ACO Comprehensive Exam March 20 and 21, Computability, Complexity and Algorithms

ACO Comprehensive Exam March 20 and 21, Computability, Complexity and Algorithms 1. Computability, Complexity and Algorithms Part a: You are given a graph G = (V,E) with edge weights w(e) > 0 for e E. You are also given a minimum cost spanning tree (MST) T. For one particular edge

More information

Graph Functional Methods for Climate Partitioning

Graph Functional Methods for Climate Partitioning Graph Functional Methods for Climate Partitioning Mathilde Mougeot - with D. Picard, V. Lefieux*, M. Marchand* Université Paris Diderot, France *Réseau Transport Electrique (RTE) Buenos Aires, 2015 Mathilde

More information

Clustering. Genome 559: Introduction to Statistical and Computational Genomics Elhanan Borenstein. Some slides adapted from Jacques van Helden

Clustering. Genome 559: Introduction to Statistical and Computational Genomics Elhanan Borenstein. Some slides adapted from Jacques van Helden Clustering Genome 559: Introduction to Statistical and Computational Genomics Elhanan Borenstein Some slides adapted from Jacques van Helden Small vs. large parsimony A quick review Fitch s algorithm:

More information

The Learning Problem and Regularization Class 03, 11 February 2004 Tomaso Poggio and Sayan Mukherjee

The Learning Problem and Regularization Class 03, 11 February 2004 Tomaso Poggio and Sayan Mukherjee The Learning Problem and Regularization 9.520 Class 03, 11 February 2004 Tomaso Poggio and Sayan Mukherjee About this class Goal To introduce a particularly useful family of hypothesis spaces called Reproducing

More information

On stars and Steiner stars. II

On stars and Steiner stars. II On stars and Steiner stars. II Adrian Dumitrescu Csaba D. Tóth Guangwu Xu June 6, 8 Abstract A Steiner star for a set P of n points in R d connects an arbitrary center point to all points of P, while a

More information

Non-linear Measure Based Process Monitoring and Fault Diagnosis

Non-linear Measure Based Process Monitoring and Fault Diagnosis Non-linear Measure Based Process Monitoring and Fault Diagnosis 12 th Annual AIChE Meeting, Reno, NV [275] Data Driven Approaches to Process Control 4:40 PM, Nov. 6, 2001 Sandeep Rajput Duane D. Bruns

More information

Least Squares Optimization

Least Squares Optimization Least Squares Optimization The following is a brief review of least squares optimization and constrained optimization techniques. Broadly, these techniques can be used in data analysis and visualization

More information

Unsupervised Anomaly Detection for High Dimensional Data

Unsupervised Anomaly Detection for High Dimensional Data Unsupervised Anomaly Detection for High Dimensional Data Department of Mathematics, Rowan University. July 19th, 2013 International Workshop in Sequential Methodologies (IWSM-2013) Outline of Talk Motivation

More information

NATIONAL UNIVERSITY OF SINGAPORE CS3230 DESIGN AND ANALYSIS OF ALGORITHMS SEMESTER II: Time Allowed 2 Hours

NATIONAL UNIVERSITY OF SINGAPORE CS3230 DESIGN AND ANALYSIS OF ALGORITHMS SEMESTER II: Time Allowed 2 Hours NATIONAL UNIVERSITY OF SINGAPORE CS3230 DESIGN AND ANALYSIS OF ALGORITHMS SEMESTER II: 2017 2018 Time Allowed 2 Hours INSTRUCTIONS TO STUDENTS 1. This assessment consists of Eight (8) questions and comprises

More information

STATS 306B: Unsupervised Learning Spring Lecture 2 April 2

STATS 306B: Unsupervised Learning Spring Lecture 2 April 2 STATS 306B: Unsupervised Learning Spring 2014 Lecture 2 April 2 Lecturer: Lester Mackey Scribe: Junyang Qian, Minzhe Wang 2.1 Recap In the last lecture, we formulated our working definition of unsupervised

More information

Empirical estimation of entropy functionals with confidence

Empirical estimation of entropy functionals with confidence Empirical estimation of entropy functionals with confidence arxiv:submit/0166914 [math.st] 19 Dec 2010 Kumar Sricharan, Department of EECS, University of ichigan Raviv Raich, School of EECS, Oregon State

More information

CSE 546 Final Exam, Autumn 2013

CSE 546 Final Exam, Autumn 2013 CSE 546 Final Exam, Autumn 0. Personal info: Name: Student ID: E-mail address:. There should be 5 numbered pages in this exam (including this cover sheet).. You can use any material you brought: any book,

More information

12 : Variational Inference I

12 : Variational Inference I 10-708: Probabilistic Graphical Models, Spring 2015 12 : Variational Inference I Lecturer: Eric P. Xing Scribes: Fattaneh Jabbari, Eric Lei, Evan Shapiro 1 Introduction Probabilistic inference is one of

More information

Cheng Soon Ong & Christian Walder. Canberra February June 2018

Cheng Soon Ong & Christian Walder. Canberra February June 2018 Cheng Soon Ong & Christian Walder Research Group and College of Engineering and Computer Science Canberra February June 218 Outlines Overview Introduction Linear Algebra Probability Linear Regression 1

More information

Lecture 3: Statistical Decision Theory (Part II)

Lecture 3: Statistical Decision Theory (Part II) Lecture 3: Statistical Decision Theory (Part II) Hao Helen Zhang Hao Helen Zhang Lecture 3: Statistical Decision Theory (Part II) 1 / 27 Outline of This Note Part I: Statistics Decision Theory (Classical

More information

Clusters. Unsupervised Learning. Luc Anselin. Copyright 2017 by Luc Anselin, All Rights Reserved

Clusters. Unsupervised Learning. Luc Anselin.   Copyright 2017 by Luc Anselin, All Rights Reserved Clusters Unsupervised Learning Luc Anselin http://spatial.uchicago.edu 1 curse of dimensionality principal components multidimensional scaling classical clustering methods 2 Curse of Dimensionality 3 Curse

More information

A Random Dot Product Model for Weighted Networks arxiv: v1 [stat.ap] 8 Nov 2016

A Random Dot Product Model for Weighted Networks arxiv: v1 [stat.ap] 8 Nov 2016 A Random Dot Product Model for Weighted Networks arxiv:1611.02530v1 [stat.ap] 8 Nov 2016 Daryl R. DeFord 1 Daniel N. Rockmore 1,2,3 1 Department of Mathematics, Dartmouth College, Hanover, NH, USA 03755

More information

Unsupervised Learning

Unsupervised Learning 2018 EE448, Big Data Mining, Lecture 7 Unsupervised Learning Weinan Zhang Shanghai Jiao Tong University http://wnzhang.net http://wnzhang.net/teaching/ee448/index.html ML Problem Setting First build and

More information

13 : Variational Inference: Loopy Belief Propagation and Mean Field

13 : Variational Inference: Loopy Belief Propagation and Mean Field 10-708: Probabilistic Graphical Models 10-708, Spring 2012 13 : Variational Inference: Loopy Belief Propagation and Mean Field Lecturer: Eric P. Xing Scribes: Peter Schulam and William Wang 1 Introduction

More information

SVD, PCA & Preprocessing

SVD, PCA & Preprocessing Chapter 1 SVD, PCA & Preprocessing Part 2: Pre-processing and selecting the rank Pre-processing Skillicorn chapter 3.1 2 Why pre-process? Consider matrix of weather data Monthly temperatures in degrees

More information

1. Entropy Estimation Let fx i g n i=1 be a point cloud in IRd, d 1. Isaac Newton Institute: k-mst 2 fx i g n i=1 are i.i.d.random vectors with unknow

1. Entropy Estimation Let fx i g n i=1 be a point cloud in IRd, d 1. Isaac Newton Institute: k-mst 2 fx i g n i=1 are i.i.d.random vectors with unknow Robust entropy estimation via pruned minimal spanning trees 1. Entropy estimation Hero Alfred of Michigan - Ann Arbor University http://www.eecs.umich.edu/ hero/hero.html 2. Minimal spanning trees (MST)

More information

Applications of Robust Optimization in Signal Processing: Beamforming and Power Control Fall 2012

Applications of Robust Optimization in Signal Processing: Beamforming and Power Control Fall 2012 Applications of Robust Optimization in Signal Processing: Beamforg and Power Control Fall 2012 Instructor: Farid Alizadeh Scribe: Shunqiao Sun 12/09/2012 1 Overview In this presentation, we study the applications

More information

Local minima and plateaus in hierarchical structures of multilayer perceptrons

Local minima and plateaus in hierarchical structures of multilayer perceptrons Neural Networks PERGAMON Neural Networks 13 (2000) 317 327 Contributed article Local minima and plateaus in hierarchical structures of multilayer perceptrons www.elsevier.com/locate/neunet K. Fukumizu*,

More information

Machine Learning and Adaptive Systems. Lectures 3 & 4

Machine Learning and Adaptive Systems. Lectures 3 & 4 ECE656- Lectures 3 & 4, Professor Department of Electrical and Computer Engineering Colorado State University Fall 2015 What is Learning? General Definition of Learning: Any change in the behavior or performance

More information

Linear and Logistic Regression. Dr. Xiaowei Huang

Linear and Logistic Regression. Dr. Xiaowei Huang Linear and Logistic Regression Dr. Xiaowei Huang https://cgi.csc.liv.ac.uk/~xiaowei/ Up to now, Two Classical Machine Learning Algorithms Decision tree learning K-nearest neighbor Model Evaluation Metrics

More information

Universal Estimation of Divergence for Continuous Distributions via Data-Dependent Partitions

Universal Estimation of Divergence for Continuous Distributions via Data-Dependent Partitions Universal Estimation of for Continuous Distributions via Data-Dependent Partitions Qing Wang, Sanjeev R. Kulkarni, Sergio Verdú Department of Electrical Engineering Princeton University Princeton, NJ 8544

More information

Homework 4, 5, 6 Solutions. > 0, and so a n 0 = n + 1 n = ( n+1 n)( n+1+ n) 1 if n is odd 1/n if n is even diverges.

Homework 4, 5, 6 Solutions. > 0, and so a n 0 = n + 1 n = ( n+1 n)( n+1+ n) 1 if n is odd 1/n if n is even diverges. 2..2(a) lim a n = 0. Homework 4, 5, 6 Solutions Proof. Let ɛ > 0. Then for n n = 2+ 2ɛ we have 2n 3 4+ ɛ 3 > ɛ > 0, so 0 < 2n 3 < ɛ, and thus a n 0 = 2n 3 < ɛ. 2..2(g) lim ( n + n) = 0. Proof. Let ɛ >

More information

Notes 6 : First and second moment methods

Notes 6 : First and second moment methods Notes 6 : First and second moment methods Math 733-734: Theory of Probability Lecturer: Sebastien Roch References: [Roc, Sections 2.1-2.3]. Recall: THM 6.1 (Markov s inequality) Let X be a non-negative

More information

Statistical Machine Learning

Statistical Machine Learning Statistical Machine Learning Christoph Lampert Spring Semester 2015/2016 // Lecture 12 1 / 36 Unsupervised Learning Dimensionality Reduction 2 / 36 Dimensionality Reduction Given: data X = {x 1,..., x

More information

SUPERVISED LEARNING: INTRODUCTION TO CLASSIFICATION

SUPERVISED LEARNING: INTRODUCTION TO CLASSIFICATION SUPERVISED LEARNING: INTRODUCTION TO CLASSIFICATION 1 Outline Basic terminology Features Training and validation Model selection Error and loss measures Statistical comparison Evaluation measures 2 Terminology

More information

Efficient and Optimal Modal-set Estimation using knn graphs

Efficient and Optimal Modal-set Estimation using knn graphs Efficient and Optimal Modal-set Estimation using knn graphs Samory Kpotufe ORFE, Princeton University Based on various results with Sanjoy Dasgupta, Kamalika Chaudhuri, Ulrike von Luxburg, Heinrich Jiang

More information

Boosting & Deep Learning

Boosting & Deep Learning Boosting & Deep Learning Ensemble Learning n So far learning methods that learn a single hypothesis, chosen form a hypothesis space that is used to make predictions n Ensemble learning à select a collection

More information

Matrix estimation by Universal Singular Value Thresholding

Matrix estimation by Universal Singular Value Thresholding Matrix estimation by Universal Singular Value Thresholding Courant Institute, NYU Let us begin with an example: Suppose that we have an undirected random graph G on n vertices. Model: There is a real symmetric

More information