Scalable Bayes Clustering for Outlier Detection Under Informative Sampling
|
|
- Magdalen Bradford
- 5 years ago
- Views:
Transcription
1 Scalable Bayes Clustering for Outlier Detection Under Informative Sampling Based on JMLR paper of T. D. Savitsky Terrance D. Savitsky Office of Survey Methods Research FCSM March 7-9, / 21
2 Motivating Dataset Monthly survey of U.S. business establishments Single stage, fixed-size, stratified sampling design Strata-indexed probabilities assigned by employment size pps establishments report employment changes (d=4) 1 x = (Employment, Production Workers, Payroll, Weekly Hours) Size variable is total employment, z x z. 7 day turnaround between submissions and publication Which establishment submissions contain reporting errors? 2 / 21
3 Estimating Population Model Under Informative Sample Finite U = (1,..., N) With data, X U = X 1,..., X N P θ. Don t fully observe the finite population. Draw a sample, S = (1,..., n N). Inclusion probabilities, P (δ i = 1) := π i correlated with X U P θ (X S ) P θ (X U ) Want to estimate outliers from P θ (X U ) using X S. Use w i 1/π i 3 / 21
4 Mixture / Cluster Model for Outlier Detection Mixture of Gaussians s i (1,..., K max ) indexes cluster memberships for i (1,..., n) (τ 1,..., τ Kmax ) cluster assignment probabilities α, number of τ p > 0, Dirichlet Process mixing measure in the limit of K max d 1 x i s i, M = (µ 1,..., µ Kmax ), σ 2, w i ind N d ( µsi, σ 2 I d ) wi s i τ iid M (1, τ 1,..., τ Kmax ) µ p G 0 iid G0 := N d ( 0, ρ 2 I d ) τ 1,..., τ Kmax D (α/k max,..., α/k max ) 4 / 21
5 Sampling-weighted Pseudo Posterior Pseudo Posterior Weighted Likelihood Priors Marginalize out τ from the joint prior, f (s, τ α) = f (s τ ) f (τ α) K d M = (µ 1,..., µ K ) n p = n i=1 1 (s i = p) number of establishments assigned to cluster, p K ( f (s, M X, w) f (X, s, M w) = N d xi µ p, σ 2 ) wi I d p=1 i:s i =p K Γ (α + 1) α Γ (α + n) K (n p 1)! p=1 K ( N d µp 0, ρ 2 ) I d. p=1 5 / 21
6 Approximate MAP as σ 2 0 Each observation assigned to its own cluster as σ 2 0 Define a constant λ and set α = exp ( λ/ ( 2σ 2)) Produces α 0 as σ 2 0 λ hyperparameter controls the size of the partition as σ 2 0 K 2σ 2 [ log f (X, s, M, w) = 2σ 2 O ( log σ 2) + w i x i µ p 2] p=1 i:s i =p + Kλ 2σ 2 O (1) 2σ 2 O (1), 6 / 21
7 Approximate MAP Optimization argmin K,s,M K p=1 i:s i =p w i x i µ p 2 + Kλ, Bayesian motivation for K-means clustering Higher value for λ reduces number of estimated clusters Goal to minimize energy expression 7 / 21
8 Add Merge Step to Algorithm Test all pairs of clusters and merge those that reduce energy Collapse 2 clusters by assigning establishments from both to single cluster Recompute cluster center, µ p Encourages fewer clusters, which supports outlier detection Reduces sensitivity to initial values 8 / 21
9 Weighted Hierarchical Clustering - Set-up Establishments, i = 1,..., n, binned to j = 1,..., J industry groups Estimate a local clustering of L max possible clusters in industry, j. Local cluster, c, in industry, j, connected to global cluster center, µ p For p (1,..., K max ) possible global clusters Local clusters across industries may share a common global cluster s j i global cluster assignment for establishment, i, in industry, j 9 / 21
10 Hierarchical Clustering Optimization argmin K,s,M K J p=1 j=1 i:s j i =p w j i xj i µ p 2 + Kλ K + Lλ L, L = J j=1 L j denotes the total number of local clusters L j denotes the number local clusters estimated for data set, j = 1,..., J K denotes the number of estimated global clusters λ K denotes penalty on number of global clusters estimated λ L denotes penalty on number of local clusters estimated w j i is the sampling weight for establishment, i, in industry, j 10 / 21
11 Selecting Penalty Parameters, (λ K, λ L ) Synthetic data, L j = 5 local clusters for j = 1,..., (J = 3) industries Sharing K = 7 global clusters X j N j (d=15) (N j = 15000, n j = 2500) establishments in (population/sample) Randomly allocated to L j = 5 in skewed distribution, (0.6, 0.25, 0.1, 0.025, 0.025) Evenly divide data into training and test sets Estimate clustering on training data and compute energy on test data 11 / 21
12 Energy steadily decreases with lower (λ K, λ L ) Estimate clustering on training data and compute energy on test data Lambda_g Energy - Test Set 8e+06 6e+06 4e+06 2e Lambda_l 12 / 21
13 Use Calinski-Harabasz (C) criterion Cohesion within each cluster, W GSS Separation between clusters, BGSS W GSS = BGSS = K p=1 w i x i µ p 2 i:s v i =k K n p µ p µ G 2 p=1 C = n K BGSS K 1 W GSS 13 / 21 µ G = n i=1 w ix i n i=1 w i K is number of global clusters
14 C finds an optimum chose the values of (λ L = 1232, λ K = 2254) Calinski_Harabasz Lambda_g Lambda_l / 21
15 Correct Clusterings Estimated Each panel presents a local clustering for industry, j (1,..., (J = 3)). We see L j = 5 with correct skewed allocation Sharing K = 7 global clusters dataset_1 dataset_2 dataset_ Number of Observations / Global Cluster
16 Merges Increase at lower values for (λ K, λ L ) Higher number of merges for lower values of (λ K, λ L ) Lambda_g 2000 num_merges Lambda_l / 21
17 Outlier Detection Simulation Study Design J = 8 local populations, X j with N j = L j = 2 local clusters, one an outlier, sharing K = 5 global clusters (d=15) 1 µ 1 = (1, 1.5, 2.0,..., 7.5, 8) µ 2 = (8, 7.5,..., 1) µ 3 = (1,..., 7, 8, 7,..., 1) µ 4 = Sampling from (1,..., 8) with replacement, d = 15 times µ 5 = Sampling from ( 2,..., 6) with replacement, d = 15 times, mean µ 5 is assigned 150 observations 17 / 21 Stratified design of H = 10 strata assign π j h variance of, Xj h B = 100 Monte Carlo draws
18 Outlier Detection Accuracy True positive # of true outliers discovered / total # of true outliers False positive # of false discoveries / total # nominated True positives measure effectiveness, False positives measure efficiency true_pos false_pos Estimation Type hier 95% CI global mbc t-kmeans hier global mbc t-kmeans global_ignore hier global mbc t-kmeans global_ignore global_ignore Outlier Cluster Assigment Statistic 18 / 21
19 Estimation Bias of Outlier Center, µ 5 For each d = 15 dimensions Dashed line presents true values % CI m p hier global mbc gl_ignore hier global mbc gl_ignore hier global mbc gl_ignore Estimation Type hier global mbc gl_ignore Outlier Cluster Centers 19 / 21
20 Take Aways Fast hierarchical clustering captures dependencies among industry clusterings. Incorporating sampling weights better detects outliers from the population. Implemented in growclusters in R. 20 / 21
21 CONTACT INFORMATION 21 / 21
Scalable Approximate Bayesian Inference for Outlier. Detection under Informative Sampling
Journal of Machine Learning Research 17 (2016) 1-49 Submitted 3/15; Revised 1/16; Published 12/16 Scalable Approximate Bayesian Inference for Outlier Detection under Informative Sampling Terrance D. Savitsky
More informationOne-Shot Learning with a Hierarchical Nonparametric Bayesian Model
One-Shot Learning with a Hierarchical Nonparametric Bayesian Model R. Salakhutdinov, J. Tenenbaum and A. Torralba MIT Technical Report, 2010 Presented by Esther Salazar Duke University June 10, 2011 E.
More informationPart I. Hierarchical clustering. Hierarchical Clustering. Hierarchical clustering. Produces a set of nested clusters organized as a
Week 9 Based in part on slides from textbook, slides of Susan Holmes Part I December 2, 2012 Hierarchical Clustering 1 / 1 Produces a set of nested clusters organized as a Hierarchical hierarchical clustering
More informationWarped Mixture Models
Warped Mixture Models Tomoharu Iwata, David Duvenaud, Zoubin Ghahramani Cambridge University Computational and Biological Learning Lab March 11, 2013 OUTLINE Motivation Gaussian Process Latent Variable
More informationClustering. Mihaela van der Schaar. January 27, Department of Engineering Science University of Oxford
Department of Engineering Science University of Oxford January 27, 2017 Many datasets consist of multiple heterogeneous subsets. Cluster analysis: Given an unlabelled data, want algorithms that automatically
More informationNote Set 4: Finite Mixture Models and the EM Algorithm
Note Set 4: Finite Mixture Models and the EM Algorithm Padhraic Smyth, Department of Computer Science University of California, Irvine Finite Mixture Models A finite mixture model with K components, for
More informationClustering Lecture 5: Mixture Model
Clustering Lecture 5: Mixture Model Jing Gao SUNY Buffalo 1 Outline Basics Motivation, definition, evaluation Methods Partitional Hierarchical Density-based Mixture model Spectral methods Advanced topics
More informationMarkov chain Monte Carlo methods
Markov chain Monte Carlo methods (supplementary material) see also the applet http://www.lbreyer.com/classic.html February 9 6 Independent Hastings Metropolis Sampler Outline Independent Hastings Metropolis
More informationClustering: Classic Methods and Modern Views
Clustering: Classic Methods and Modern Views Marina Meilă University of Washington mmp@stat.washington.edu June 22, 2015 Lorentz Center Workshop on Clusters, Games and Axioms Outline Paradigms for clustering
More informationCOMS 4771 Clustering. Nakul Verma
COMS 4771 Clustering Nakul Verma Supervised Learning Data: Supervised learning Assumption: there is a (relatively simple) function such that for most i Learning task: given n examples from the data, find
More informationIntroduction to Mobile Robotics
Introduction to Mobile Robotics Clustering Wolfram Burgard Cyrill Stachniss Giorgio Grisetti Maren Bennewitz Christian Plagemann Clustering (1) Common technique for statistical data analysis (machine learning,
More informationStatistics 202: Data Mining. c Jonathan Taylor. Outliers Based in part on slides from textbook, slides of Susan Holmes.
Outliers Based in part on slides from textbook, slides of Susan Holmes December 2, 2012 1 / 1 Concepts What is an outlier? The set of data points that are considerably different than the remainder of the
More informationAn Efficient Model Selection for Gaussian Mixture Model in a Bayesian Framework
IEEE SIGNAL PROCESSING LETTERS, VOL. XX, NO. XX, XXX 23 An Efficient Model Selection for Gaussian Mixture Model in a Bayesian Framework Ji Won Yoon arxiv:37.99v [cs.lg] 3 Jul 23 Abstract In order to cluster
More informationMixture Models and the EM Algorithm
Mixture Models and the EM Algorithm Padhraic Smyth, Department of Computer Science University of California, Irvine c 2017 1 Finite Mixture Models Say we have a data set D = {x 1,..., x N } where x i is
More informationMachine Learning A WS15/16 1sst KU Version: January 11, b) [1 P] For the probability distribution P (A, B, C, D) with the factorization
Machine Learning A 708.064 WS15/16 1sst KU Version: January 11, 2016 Exercises Problems marked with * are optional. 1 Conditional Independence I [3 P] a) [1 P] For the probability distribution P (A, B,
More informationMachine Learning A W 1sst KU. b) [1 P] Give an example for a probability distributions P (A, B, C) that disproves
Machine Learning A 708.064 11W 1sst KU Exercises Problems marked with * are optional. 1 Conditional Independence I [2 P] a) [1 P] Give an example for a probability distribution P (A, B, C) that disproves
More informationClustering web search results
Clustering K-means Machine Learning CSE546 Emily Fox University of Washington November 4, 2013 1 Clustering images Set of Images [Goldberger et al.] 2 1 Clustering web search results 3 Some Data 4 2 K-means
More informationStatistical Matching using Fractional Imputation
Statistical Matching using Fractional Imputation Jae-Kwang Kim 1 Iowa State University 1 Joint work with Emily Berg and Taesung Park 1 Introduction 2 Classical Approaches 3 Proposed method 4 Application:
More informationCS281 Section 9: Graph Models and Practical MCMC
CS281 Section 9: Graph Models and Practical MCMC Scott Linderman November 11, 213 Now that we have a few MCMC inference algorithms in our toolbox, let s try them out on some random graph models. Graphs
More informationK-means and Hierarchical Clustering
K-means and Hierarchical Clustering Xiaohui Xie University of California, Irvine K-means and Hierarchical Clustering p.1/18 Clustering Given n data points X = {x 1, x 2,, x n }. Clustering is the partitioning
More informationBayesian Inference for Sample Surveys
Bayesian Inference for Sample Surveys Trivellore Raghunathan (Raghu) Director, Survey Research Center Professor of Biostatistics University of Michigan Distinctive features of survey inference 1. Primary
More informationINF 4300 Classification III Anne Solberg The agenda today:
INF 4300 Classification III Anne Solberg 28.10.15 The agenda today: More on estimating classifier accuracy Curse of dimensionality and simple feature selection knn-classification K-means clustering 28.10.15
More informationMachine Learning (BSMC-GA 4439) Wenke Liu
Machine Learning (BSMC-GA 4439) Wenke Liu 01-31-017 Outline Background Defining proximity Clustering methods Determining number of clusters Comparing two solutions Cluster analysis as unsupervised Learning
More information10-701/15-781, Fall 2006, Final
-7/-78, Fall 6, Final Dec, :pm-8:pm There are 9 questions in this exam ( pages including this cover sheet). If you need more room to work out your answer to a question, use the back of the page and clearly
More informationECE 5424: Introduction to Machine Learning
ECE 5424: Introduction to Machine Learning Topics: Unsupervised Learning: Kmeans, GMM, EM Readings: Barber 20.1-20.3 Stefan Lee Virginia Tech Tasks Supervised Learning x Classification y Discrete x Regression
More informationMachine Learning and Data Mining. Clustering (1): Basics. Kalev Kask
Machine Learning and Data Mining Clustering (1): Basics Kalev Kask Unsupervised learning Supervised learning Predict target value ( y ) given features ( x ) Unsupervised learning Understand patterns of
More informationBayesian Spatiotemporal Modeling with Hierarchical Spatial Priors for fmri
Bayesian Spatiotemporal Modeling with Hierarchical Spatial Priors for fmri Galin L. Jones 1 School of Statistics University of Minnesota March 2015 1 Joint with Martin Bezener and John Hughes Experiment
More informationK-Means and Gaussian Mixture Models
K-Means and Gaussian Mixture Models David Rosenberg New York University June 15, 2015 David Rosenberg (New York University) DS-GA 1003 June 15, 2015 1 / 43 K-Means Clustering Example: Old Faithful Geyser
More informationImage analysis. Computer Vision and Classification Image Segmentation. 7 Image analysis
7 Computer Vision and Classification 413 / 458 Computer Vision and Classification The k-nearest-neighbor method The k-nearest-neighbor (knn) procedure has been used in data analysis and machine learning
More informationExpectation Maximization. Machine Learning 10701/15781 Carlos Guestrin Carnegie Mellon University
Expectation Maximization Machine Learning 10701/15781 Carlos Guestrin Carnegie Mellon University April 10 th, 2006 1 Announcements Reminder: Project milestone due Wednesday beginning of class 2 Coordinate
More informationUnsupervised Learning
Networks for Pattern Recognition, 2014 Networks for Single Linkage K-Means Soft DBSCAN PCA Networks for Kohonen Maps Linear Vector Quantization Networks for Problems/Approaches in Machine Learning Supervised
More informationRandomized Algorithms for Fast Bayesian Hierarchical Clustering
Randomized Algorithms for Fast Bayesian Hierarchical Clustering Katherine A. Heller and Zoubin Ghahramani Gatsby Computational Neuroscience Unit University College ondon, ondon, WC1N 3AR, UK {heller,zoubin}@gatsby.ucl.ac.uk
More informationMachine Learning A W 1sst KU. b) [1 P] For the probability distribution P (A, B, C, D) with the factorization
Machine Learning A 708.064 13W 1sst KU Exercises Problems marked with * are optional. 1 Conditional Independence a) [1 P] For the probability distribution P (A, B, C, D) with the factorization P (A, B,
More informationQuantitative Biology II!
Quantitative Biology II! Lecture 3: Markov Chain Monte Carlo! March 9, 2015! 2! Plan for Today!! Introduction to Sampling!! Introduction to MCMC!! Metropolis Algorithm!! Metropolis-Hastings Algorithm!!
More informationToday. Lecture 4: Last time. The EM algorithm. We examine clustering in a little more detail; we went over it a somewhat quickly last time
Today Lecture 4: We examine clustering in a little more detail; we went over it a somewhat quickly last time The CAD data will return and give us an opportunity to work with curves (!) We then examine
More informationEstimating Labels from Label Proportions
Estimating Labels from Label Proportions Novi Quadrianto Novi.Quad@gmail.com The Australian National University, Australia NICTA, Statistical Machine Learning Program, Australia Joint work with Alex Smola,
More informationA Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection (Kohavi, 1995)
A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection (Kohavi, 1995) Department of Information, Operations and Management Sciences Stern School of Business, NYU padamopo@stern.nyu.edu
More informationIntroduction to Machine Learning CMU-10701
Introduction to Machine Learning CMU-10701 Clustering and EM Barnabás Póczos & Aarti Singh Contents Clustering K-means Mixture of Gaussians Expectation Maximization Variational Methods 2 Clustering 3 K-
More informationCluster analysis formalism, algorithms. Department of Cybernetics, Czech Technical University in Prague.
Cluster analysis formalism, algorithms Jiří Kléma Department of Cybernetics, Czech Technical University in Prague http://ida.felk.cvut.cz poutline motivation why clustering? applications, clustering as
More information10. MLSP intro. (Clustering: K-means, EM, GMM, etc.)
10. MLSP intro. (Clustering: K-means, EM, GMM, etc.) Rahil Mahdian 01.04.2016 LSV Lab, Saarland University, Germany What is clustering? Clustering is the classification of objects into different groups,
More informationSGN (4 cr) Chapter 11
SGN-41006 (4 cr) Chapter 11 Clustering Jussi Tohka & Jari Niemi Department of Signal Processing Tampere University of Technology February 25, 2014 J. Tohka & J. Niemi (TUT-SGN) SGN-41006 (4 cr) Chapter
More informationThe exam is closed book, closed notes except your one-page (two-sided) cheat sheet.
CS 189 Spring 2015 Introduction to Machine Learning Final You have 2 hours 50 minutes for the exam. The exam is closed book, closed notes except your one-page (two-sided) cheat sheet. No calculators or
More informationMachine Learning. B. Unsupervised Learning B.1 Cluster Analysis. Lars Schmidt-Thieme, Nicolas Schilling
Machine Learning B. Unsupervised Learning B.1 Cluster Analysis Lars Schmidt-Thieme, Nicolas Schilling Information Systems and Machine Learning Lab (ISMLL) Institute for Computer Science University of Hildesheim,
More informationUnsupervised Learning
Unsupervised Learning Learning without Class Labels (or correct outputs) Density Estimation Learn P(X) given training data for X Clustering Partition data into clusters Dimensionality Reduction Discover
More informationDATA MINING LECTURE 7. Hierarchical Clustering, DBSCAN The EM Algorithm
DATA MINING LECTURE 7 Hierarchical Clustering, DBSCAN The EM Algorithm CLUSTERING What is a Clustering? In general a grouping of objects such that the objects in a group (cluster) are similar (or related)
More informationVariational Inference for Non-Stationary Distributions. Arsen Mamikonyan
Variational Inference for Non-Stationary Distributions by Arsen Mamikonyan B.S. EECS, Massachusetts Institute of Technology (2012) B.S. Physics, Massachusetts Institute of Technology (2012) Submitted to
More informationMachine Learning (BSMC-GA 4439) Wenke Liu
Machine Learning (BSMC-GA 4439) Wenke Liu 01-25-2018 Outline Background Defining proximity Clustering methods Determining number of clusters Other approaches Cluster analysis as unsupervised Learning Unsupervised
More informationMachine Learning Department School of Computer Science Carnegie Mellon University. K- Means + GMMs
10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University K- Means + GMMs Clustering Readings: Murphy 25.5 Bishop 12.1, 12.3 HTF 14.3.0 Mitchell
More informationMissing Data Analysis for the Employee Dataset
Missing Data Analysis for the Employee Dataset 67% of the observations have missing values! Modeling Setup For our analysis goals we would like to do: Y X N (X, 2 I) and then interpret the coefficients
More informationThe exam is closed book, closed notes except your one-page (two-sided) cheat sheet.
CS 189 Spring 2015 Introduction to Machine Learning Final You have 2 hours 50 minutes for the exam. The exam is closed book, closed notes except your one-page (two-sided) cheat sheet. No calculators or
More informationMonte Carlo for Spatial Models
Monte Carlo for Spatial Models Murali Haran Department of Statistics Penn State University Penn State Computational Science Lectures April 2007 Spatial Models Lots of scientific questions involve analyzing
More informationMultiDimensional Signal Processing Master Degree in Ingegneria delle Telecomunicazioni A.A
MultiDimensional Signal Processing Master Degree in Ingegneria delle Telecomunicazioni A.A. 205-206 Pietro Guccione, PhD DEI - DIPARTIMENTO DI INGEGNERIA ELETTRICA E DELL INFORMAZIONE POLITECNICO DI BARI
More informationA Dendrogram. Bioinformatics (Lec 17)
A Dendrogram 3/15/05 1 Hierarchical Clustering [Johnson, SC, 1967] Given n points in R d, compute the distance between every pair of points While (not done) Pick closest pair of points s i and s j and
More informationFeature LDA: a Supervised Topic Model for Automatic Detection of Web API Documentations from the Web
Feature LDA: a Supervised Topic Model for Automatic Detection of Web API Documentations from the Web Chenghua Lin, Yulan He, Carlos Pedrinaci, and John Domingue Knowledge Media Institute, The Open University
More informationSampling Table Configulations for the Hierarchical Poisson-Dirichlet Process
Sampling Table Configulations for the Hierarchical Poisson-Dirichlet Process Changyou Chen,, Lan Du,, Wray Buntine, ANU College of Engineering and Computer Science The Australian National University National
More information08 An Introduction to Dense Continuous Robotic Mapping
NAVARCH/EECS 568, ROB 530 - Winter 2018 08 An Introduction to Dense Continuous Robotic Mapping Maani Ghaffari March 14, 2018 Previously: Occupancy Grid Maps Pose SLAM graph and its associated dense occupancy
More informationSensor Tasking and Control
Sensor Tasking and Control Outline Task-Driven Sensing Roles of Sensor Nodes and Utilities Information-Based Sensor Tasking Joint Routing and Information Aggregation Summary Introduction To efficiently
More informationClustering K-means. Machine Learning CSEP546 Carlos Guestrin University of Washington February 18, Carlos Guestrin
Clustering K-means Machine Learning CSEP546 Carlos Guestrin University of Washington February 18, 2014 Carlos Guestrin 2005-2014 1 Clustering images Set of Images [Goldberger et al.] Carlos Guestrin 2005-2014
More informationSpatial Latent Dirichlet Allocation
Spatial Latent Dirichlet Allocation Xiaogang Wang and Eric Grimson Computer Science and Computer Science and Artificial Intelligence Lab Massachusetts Tnstitute of Technology, Cambridge, MA, 02139, USA
More informationMini-project 2 CMPSCI 689 Spring 2015 Due: Tuesday, April 07, in class
Mini-project 2 CMPSCI 689 Spring 2015 Due: Tuesday, April 07, in class Guidelines Submission. Submit a hardcopy of the report containing all the figures and printouts of code in class. For readability
More informationIBL and clustering. Relationship of IBL with CBR
IBL and clustering Distance based methods IBL and knn Clustering Distance based and hierarchical Probability-based Expectation Maximization (EM) Relationship of IBL with CBR + uses previously processed
More informationMULTI-DIMENSIONAL MONTE CARLO INTEGRATION
CS580: Computer Graphics KAIST School of Computing Chapter 3 MULTI-DIMENSIONAL MONTE CARLO INTEGRATION 2 1 Monte Carlo Integration This describes a simple technique for the numerical evaluation of integrals
More informationDivide and Conquer Kernel Ridge Regression
Divide and Conquer Kernel Ridge Regression Yuchen Zhang John Duchi Martin Wainwright University of California, Berkeley COLT 2013 Yuchen Zhang (UC Berkeley) Divide and Conquer KRR COLT 2013 1 / 15 Problem
More informationClient Dependent GMM-SVM Models for Speaker Verification
Client Dependent GMM-SVM Models for Speaker Verification Quan Le, Samy Bengio IDIAP, P.O. Box 592, CH-1920 Martigny, Switzerland {quan,bengio}@idiap.ch Abstract. Generative Gaussian Mixture Models (GMMs)
More informationFMA901F: Machine Learning Lecture 3: Linear Models for Regression. Cristian Sminchisescu
FMA901F: Machine Learning Lecture 3: Linear Models for Regression Cristian Sminchisescu Machine Learning: Frequentist vs. Bayesian In the frequentist setting, we seek a fixed parameter (vector), with value(s)
More informationClustering K-means. Machine Learning CSEP546 Carlos Guestrin University of Washington February 18, Carlos Guestrin
Clustering K-means Machine Learning CSEP546 Carlos Guestrin University of Washington February 18, 2014 Carlos Guestrin 2005-2014 1 Clustering images Set of Images [Goldberger et al.] Carlos Guestrin 2005-2014
More information10701 Machine Learning. Clustering
171 Machine Learning Clustering What is Clustering? Organizing data into clusters such that there is high intra-cluster similarity low inter-cluster similarity Informally, finding natural groupings among
More informationOutline. Bayesian Data Analysis Hierarchical models. Rat tumor data. Errandum: exercise GCSR 3.11
Outline Bayesian Data Analysis Hierarchical models Helle Sørensen May 15, 2009 Today: More about the rat tumor data: model, derivation of posteriors, the actual computations in R. : a hierarchical normal
More informationCluster Analysis. Jia Li Department of Statistics Penn State University. Summer School in Statistics for Astronomers IV June 9-14, 2008
Cluster Analysis Jia Li Department of Statistics Penn State University Summer School in Statistics for Astronomers IV June 9-1, 8 1 Clustering A basic tool in data mining/pattern recognition: Divide a
More informationMultiple Model Estimation : The EM Algorithm & Applications
Multiple Model Estimation : The EM Algorithm & Applications Princeton University COS 429 Lecture Nov. 13, 2007 Harpreet S. Sawhney hsawhney@sarnoff.com Recapitulation Problem of motion estimation Parametric
More informationCS 1675 Introduction to Machine Learning Lecture 18. Clustering. Clustering. Groups together similar instances in the data sample
CS 1675 Introduction to Machine Learning Lecture 18 Clustering Milos Hauskrecht milos@cs.pitt.edu 539 Sennott Square Clustering Groups together similar instances in the data sample Basic clustering problem:
More informationThe Multi Stage Gibbs Sampling: Data Augmentation Dutch Example
The Multi Stage Gibbs Sampling: Data Augmentation Dutch Example Rebecca C. Steorts Bayesian Methods and Modern Statistics: STA 360/601 Module 8 1 Example: Data augmentation / Auxiliary variables A commonly-used
More informationData Mining Chapter 9: Descriptive Modeling Fall 2011 Ming Li Department of Computer Science and Technology Nanjing University
Data Mining Chapter 9: Descriptive Modeling Fall 2011 Ming Li Department of Computer Science and Technology Nanjing University Descriptive model A descriptive model presents the main features of the data
More informationHomework #4 Programming Assignment Due: 11:59 pm, November 4, 2018
CSCI 567, Fall 18 Haipeng Luo Homework #4 Programming Assignment Due: 11:59 pm, ovember 4, 2018 General instructions Your repository will have now a directory P4/. Please do not change the name of this
More informationMissing Data Analysis for the Employee Dataset
Missing Data Analysis for the Employee Dataset 67% of the observations have missing values! Modeling Setup Random Variables: Y i =(Y i1,...,y ip ) 0 =(Y i,obs, Y i,miss ) 0 R i =(R i1,...,r ip ) 0 ( 1
More informationCOMP 551 Applied Machine Learning Lecture 13: Unsupervised learning
COMP 551 Applied Machine Learning Lecture 13: Unsupervised learning Associate Instructor: Herke van Hoof (herke.vanhoof@mail.mcgill.ca) Slides mostly by: (jpineau@cs.mcgill.ca) Class web page: www.cs.mcgill.ca/~jpineau/comp551
More informationBehavioral Data Mining. Lecture 18 Clustering
Behavioral Data Mining Lecture 18 Clustering Outline Why? Cluster quality K-means Spectral clustering Generative Models Rationale Given a set {X i } for i = 1,,n, a clustering is a partition of the X i
More informationSpatial Outlier Detection
Spatial Outlier Detection Chang-Tien Lu Department of Computer Science Northern Virginia Center Virginia Tech Joint work with Dechang Chen, Yufeng Kou, Jiang Zhao 1 Spatial Outlier A spatial data point
More informationBlending of Probability and Convenience Samples:
Blending of Probability and Convenience Samples: Applications to a Survey of Military Caregivers Michael Robbins RAND Corporation Collaborators: Bonnie Ghosh-Dastidar, Rajeev Ramchand September 25, 2017
More informationGAMs semi-parametric GLMs. Simon Wood Mathematical Sciences, University of Bath, U.K.
GAMs semi-parametric GLMs Simon Wood Mathematical Sciences, University of Bath, U.K. Generalized linear models, GLM 1. A GLM models a univariate response, y i as g{e(y i )} = X i β where y i Exponential
More informationMultiple Model Estimation : The EM Algorithm & Applications
Multiple Model Estimation : The EM Algorithm & Applications Princeton University COS 429 Lecture Dec. 4, 2008 Harpreet S. Sawhney hsawhney@sarnoff.com Plan IBR / Rendering applications of motion / pose
More informationNetwork Traffic Measurements and Analysis
DEIB - Politecnico di Milano Fall, 2017 Introduction Often, we have only a set of features x = x 1, x 2,, x n, but no associated response y. Therefore we are not interested in prediction nor classification,
More informationAnalysis of Incomplete Multivariate Data
Analysis of Incomplete Multivariate Data J. L. Schafer Department of Statistics The Pennsylvania State University USA CHAPMAN & HALL/CRC A CR.C Press Company Boca Raton London New York Washington, D.C.
More informationComputer vision: models, learning and inference. Chapter 10 Graphical Models
Computer vision: models, learning and inference Chapter 10 Graphical Models Independence Two variables x 1 and x 2 are independent if their joint probability distribution factorizes as Pr(x 1, x 2 )=Pr(x
More informationProblem 1 (20 pt) Answer the following questions, and provide an explanation for each question.
Problem 1 Answer the following questions, and provide an explanation for each question. (5 pt) Can linear regression work when all X values are the same? When all Y values are the same? (5 pt) Can linear
More informationIntroduction to Pattern Recognition Part II. Selim Aksoy Bilkent University Department of Computer Engineering
Introduction to Pattern Recognition Part II Selim Aksoy Bilkent University Department of Computer Engineering saksoy@cs.bilkent.edu.tr RETINA Pattern Recognition Tutorial, Summer 2005 Overview Statistical
More informationExpectation Maximization: Inferring model parameters and class labels
Expectation Maximization: Inferring model parameters and class labels Emily Fox University of Washington February 27, 2017 Mixture of Gaussian recap 1 2/27/2017 Jumble of unlabeled images HISTOGRAM blue
More informationClustering. Shishir K. Shah
Clustering Shishir K. Shah Acknowledgement: Notes by Profs. M. Pollefeys, R. Jin, B. Liu, Y. Ukrainitz, B. Sarel, D. Forsyth, M. Shah, K. Grauman, and S. K. Shah Clustering l Clustering is a technique
More informationPackage EBglmnet. January 30, 2016
Type Package Package EBglmnet January 30, 2016 Title Empirical Bayesian Lasso and Elastic Net Methods for Generalized Linear Models Version 4.1 Date 2016-01-15 Author Anhui Huang, Dianting Liu Maintainer
More informationData Mining. Clustering. Hamid Beigy. Sharif University of Technology. Fall 1394
Data Mining Clustering Hamid Beigy Sharif University of Technology Fall 1394 Hamid Beigy (Sharif University of Technology) Data Mining Fall 1394 1 / 31 Table of contents 1 Introduction 2 Data matrix and
More informationSTAT 725 Notes Monte Carlo Integration
STAT 725 Notes Monte Carlo Integration Two major classes of numerical problems arise in statistical inference: optimization and integration. We have already spent some time discussing different optimization
More informationCalibration and emulation of TIE-GCM
Calibration and emulation of TIE-GCM Serge Guillas School of Mathematics Georgia Institute of Technology Jonathan Rougier University of Bristol Big Thanks to Crystal Linkletter (SFU-SAMSI summer school)
More informationClustering and The Expectation-Maximization Algorithm
Clustering and The Expectation-Maximization Algorithm Unsupervised Learning Marek Petrik 3/7 Some of the figures in this presentation are taken from An Introduction to Statistical Learning, with applications
More informationBuilding Classifiers using Bayesian Networks
Building Classifiers using Bayesian Networks Nir Friedman and Moises Goldszmidt 1997 Presented by Brian Collins and Lukas Seitlinger Paper Summary The Naive Bayes classifier has reasonable performance
More informationDeep Generative Models Variational Autoencoders
Deep Generative Models Variational Autoencoders Sudeshna Sarkar 5 April 2017 Generative Nets Generative models that represent probability distributions over multiple variables in some way. Directed Generative
More informationIntroduction to Mobile Robotics Bayes Filter Particle Filter and Monte Carlo Localization. Wolfram Burgard
Introduction to Mobile Robotics Bayes Filter Particle Filter and Monte Carlo Localization Wolfram Burgard 1 Motivation Recall: Discrete filter Discretize the continuous state space High memory complexity
More informationExpectation Maximization: Inferring model parameters and class labels
Expectation Maximization: Inferring model parameters and class labels Emily Fox University of Washington February 27, 2017 Mixture of Gaussian recap 1 2/26/17 Jumble of unlabeled images HISTOGRAM blue
More informationApplications of admixture models
Applications of admixture models CM226: Machine Learning for Bioinformatics. Fall 2016 Sriram Sankararaman Acknowledgments: Fei Sha, Ameet Talwalkar, Alkes Price Applications of admixture models 1 / 27
More informationUnsupervised: no target value to predict
Clustering Unsupervised: no target value to predict Differences between models/algorithms: Exclusive vs. overlapping Deterministic vs. probabilistic Hierarchical vs. flat Incremental vs. batch learning
More informationA GENERAL GIBBS SAMPLING ALGORITHM FOR ANALYZING LINEAR MODELS USING THE SAS SYSTEM
A GENERAL GIBBS SAMPLING ALGORITHM FOR ANALYZING LINEAR MODELS USING THE SAS SYSTEM Jayawant Mandrekar, Daniel J. Sargent, Paul J. Novotny, Jeff A. Sloan Mayo Clinic, Rochester, MN 55905 ABSTRACT A general
More information