Likelihood, MLE & EM for Gaussian Mixture Clustering. Nick Duffield Texas A&M University

Size: px
Start display at page:

Download "Likelihood, MLE & EM for Gaussian Mixture Clustering. Nick Duffield Texas A&M University"

Transcription

1 Likelihood, MLE & EM for Gaussian Mixture Clustering Nick Duffield Texas A&M University

2 Probability vs. Likelihood Probability: predict unknown outcomes based on known parameters: P(x q) Likelihood: estimate unknown parameters based on known outcomes: L(q x) = p(x q) Coin-flip example: q is probability of heads (parameter) x = HHHTTH is outcome form 6 flips

3 Likelihood for Coin-flip Example Probability of outcome given parameter: p(x = HHHTTH q = 0.5) = = Likelihood of parameter given outcome: L(q = 0.5 x = HHHTTH) = p(x q) = General Θ L(Θ HHHTTH) = Θ 4 (1-Θ) Likelihood maximal when q = Likelihood function not a probability density

4 Coin Flip MLE details L(Θ HHHTTH) = Θ 4 (1-Θ) Differentiate log L w.r.t. Θ: 4/Θ /(1-Θ) = 0 à Θ = /3 Maximizer since logarithm is concave Intuitive result: MLE of H probability Θ = fraction of H in sample

5 Likelihood for Cont. Distributions Six samples {-3, -, -1, 1,, 3} believed to be drawn from some Gaussian N(0, s ) Likelihood of s: L( s { -3,-, -1,1,,3}) = p( x = -3 s ) p( x = - s )! p( x = 3 s ) Maximum likelihood: s = (-3) + (-) + (-1) =.16

6 Likelihood for Cont. Distributions Six samples {-3, -, -1, 1,, 3} believed to be drawn from some Gaussian N(0, s ) Likelihood of s: L( s { -3,-, -1,1,,3}) = p( x = -3 s ) p( x = - s )! p( x = 3 s ) Maximum likelihood: s = (-3) + (-) + (-1) =.16 Intuitive: MLE s = sample variance

7 Maximum Likelihood Estimate Parameterized family of distributions of some r.v. X P[X θ] for θ in some paramter set Likelihood L(θ,X) = P[X θ] MLE = argmax θ L(θ,X) Generally can t compute explicitly Single point f(x j ) = Σ k i=1 f(x j μ i, Σ i )P(C i ) P[X θ]=prod j f(x j ) Log-LLHD log P(X θ)=σ n j=1 log f(x j ) = Σ n j=1 log Σ k i=1f(x j μ i, Σ i )P(C i ) Find max by differentiation? Difficult due to sum inside logarithms

8 Latent data Observations X ={x 1,x,.,x n } Suppose latent data Y, unobserved, that explains the observations E.g. if clustering with mixture of k Gaussians Latent variables Y = {y 1,y,.,yn} where each y i in {1,,k} tells which mixture component i actually followed. Parameters θ = (P(C i )) describe joint distribution of P θ (X,Y) of X,Y Y part: P(C i ) = probability to be in component i Distribution of X given Y: μ i, Σ i parametrize Gaussian distribution of x in component i Problem: we don t know the y i Call (X,Y) complete data Contrast with observed data X Complete data likelihood L(θ X,Y) = P θ (X,Y)

9 Expectation-Maximization Let E θ denote the expectation w/ parameter θ Expectation Step: Compute Expected value of the complete data log likelihood, conditioned on observed data X Q(θ, θ) = E θ [log L(θ X,Y) X] Maximization step: given θ, find the parameters f(θ) = arg max θ Q(θ, θ)

10 EM Procedure: Initialize θ(0) Iterate E and M steps sequence of iterates θ(n+1) = f(θ(n)) Iterate until some stopping criterion is met, e.g., small successive differences until θ(n+1) θ(n) < ε Declare victory and hope θ is MLE of the original problem: argmax L(θ,X)

11 3 questions What is the unobserved data Y? How does it relate to any given problem How do I know its distribution? How is this related to the MLE problem? Function Q(θ, θ) = E θ [log L(θ X,Y] X] New parameters f(θ) = arg max θ Q(θ, θ) Find parameters θ that maximize E log likelihood Seems to have something to do with MLE How to find maximizer to compute iterates f(θ)

12 Why Expectation Maximization? P θ (X,Y) = P θ (X) P θ (Y X) log P θ (X) = log P θ (X,Y)- log P θ (Y X) log L(θ X) = log L(θ X,Y ) - log P θ (Y X) Take expectation E θ conditional on X log L(θ X) = Q(θ, θ) + H(θ, θ) Where H(θ, θ) = - E θ [ log P θ (Y X) X ]

13 Why Expectation Maximization? Recap: log L(θ X) = Q(θ, θ) + H(θ, θ) Suppose θ* = argmax θ Q(θ, θ) log L(θ* X) log L(θ X) = Q(θ*, θ)- Q(θ, θ) + (H(θ*, θ)-h(θ, θ)) H(θ*, θ)-h(θ, θ) By Gibbs inequality (see later): H(θ*, θ)-h(θ, θ) 0 Then conclude that log L(θ* X) L(θ X) Observed data likelihood is higher for θ* than for θ

14 Expectation-Maximization: Monotonicity Map θàf(θ)=θ* Sequence θ(n+1) = f(θ(n)). L(θ(n) X) is non-decreasing function of n Best case: L(θ(n) X) increases monotonically to a limit which is the ML θ(n) converges to MLE argmax θ L(θ X) Caveat: L(θ(n) X) could converge to a local maximum of the likelihood global maximum local maximum global maximum L(θ(n) X) θ

15 Gibbs Inequality Theorem: If p and q are two probability distributions with q i = 0 - à p i = 0 D(p,q) = Σ i p i log (p i / q i ) 0 with equality iff p = q H(θ, θ) = - E θ [ log P θ (Y X) X ] = Σ y P θ (Y=y X) log P θ (Y=y X) H(θ*, θ)-h(θ, θ) = Σ y P θ (Y=y X) log P θ (Y=y X) - P θ (Y=y X) log P θ* (Y=y X) = Σ y P θ (Y=y X) {log P θ (Y=y X)/P θ* (Y=y X)} = D(P θ (Y X), P θ* (Y X) 0 by Gibbs

16 Proof of Gibbs Inequality Want to show D(p,q) = Σ i p i log (p i / q i ) 0 g(x) = log(x) a concave function, derivative 1/x is decreasing log x log 1 g (1)(x-1)=x-1 with equality only of x =1. - log x = log(1/x) < 1/x-1 so log x > 1-1/x log p/q > 1 q/p Σ i p i log (p i / q i ) Σ i p i (1-q i /p i ) =Σ i p i q i =1-1 =0 with equality only if p i = q i for all i

17 When does EM converge to MLE? Certain abstract conditions but sometimes difficult to check. Theorem: If L(θ,X) has unique maximum and (d/dθ)q(θ, θ ) is continuous in θ and θ Then EM sequence converges to MLE

18 Gaussian Mixture models Observed Data LLHD: log P(X θ)=σ n j=1 log f(x j ) = Σ n j=1 log Σ k i=1f(x j μ i, Σ i )P(C i ) Complete data: Each point x j comes with vector c j = (c j1,,c jk ) c j indicates which component j lies in: c ji = 1 if j in component i and zero otherwise. Y = {c j } is latent or unobserved data. E[c ji ] = P[C i x j ] = w ij

19 Full Data Likelihood Full data likelihood: Suppose we know the c ji as data, i.e. which component i each point j belongs to For each point x j f(x j, c j ) = Π k i=1 (f(x j μ i, Σ i )P(C i ))**c ji c ji = 1 for exactly 1 of the i: Terms in product for all other i are 1 P(X,Y θ)=π n j=1f(x j, c j )=Π n j=1π k i=1 (f(x j μ i, Σ i )P(C i ))**c ji log P(X,Y θ) = Σ n j=1 Σ n j=1c ji log {f(x j μ i, Σ i )P(C i )}

20 Computation of Q Much nicer than for observed data likelihood no sum inside log Q(θ, θ) = E θ [log L(θ X,Y) X] = E θ [ Σ n j=1 Σ k i=1c ji {log f(x j μ i, Σ i ) + log P (C i )} X] Conditioned on X, so the x j are just constant E θ [c ji ] = P[C i x j ] = w ij Q(θ, θ) = Σ n j=1 Σ n j=1 w ij {log f(x j μ i, Σ i ) + log P (C i ) }

21 Computation of maximizer (1-dim) Recap: Q(θ, θ) = Σ k i=1 Σ n j=1 w ij {log f(x j μ i, Σ i ) + log P (C i ) } log f(x j μ i, Σ i ) = -(x j -μ i ) /(σ i ) - log σ i + const. Differentiate w.r.t. μ i : Σ n j=1 w ij (x j -μ i ) = 0 Occurs when μ i = μ i * = Σ n j=1 w ij x j / Σ n j=1 w ij Differentiate w.r.t. σ i -Σ n j=1 { w ij (x j -μ i ) / (σ i ) 3-1/ σ i } = 0 Occurs when (σ i ) =(σ* i ) = Σ n j=1 w ij (x j -μ i ) / Σ n j=1 w ij

22 Computation of maximizer (1-dim) Recap: Q(θ, θ) = Σ k i=1 Σ n j=1 w ij {log f(x j μ i, Σ i ) + log P (C i ) } Differentiate w.r.t. P (C i ) Subject to constraint Σ k i=1p (C i ) = 1 Σ n j=1 w ij / P (C i ) = constant independent of i Occurs when P (C i ) = Σ n j=1 w ij / n Maximizer Have recovered stated iteration of parameters μ i à μ i*, Σ i à Σ i*, P(C i ) à P*(C i )

Expectation Maximization (EM) Algorithm. Each has it s own probability of seeing H on any one flip. Let. p 1 = P ( H on Coin 1 )

Expectation Maximization (EM) Algorithm. Each has it s own probability of seeing H on any one flip. Let. p 1 = P ( H on Coin 1 ) Expectation Maximization (EM Algorithm Motivating Example: Have two coins: Coin 1 and Coin 2 Each has it s own probability of seeing H on any one flip. Let p 1 = P ( H on Coin 1 p 2 = P ( H on Coin 2 Select

More information

Gaussian Mixture Models

Gaussian Mixture Models Gaussian Mixture Models Pradeep Ravikumar Co-instructor: Manuela Veloso Machine Learning 10-701 Some slides courtesy of Eric Xing, Carlos Guestrin (One) bad case for K- means Clusters may overlap Some

More information

Lecture 6: Gaussian Mixture Models (GMM)

Lecture 6: Gaussian Mixture Models (GMM) Helsinki Institute for Information Technology Lecture 6: Gaussian Mixture Models (GMM) Pedram Daee 3.11.2015 Outline Gaussian Mixture Models (GMM) Models Model families and parameters Parameter learning

More information

Mixture Models & EM. Nicholas Ruozzi University of Texas at Dallas. based on the slides of Vibhav Gogate

Mixture Models & EM. Nicholas Ruozzi University of Texas at Dallas. based on the slides of Vibhav Gogate Mixture Models & EM icholas Ruozzi University of Texas at Dallas based on the slides of Vibhav Gogate Previously We looed at -means and hierarchical clustering as mechanisms for unsupervised learning -means

More information

Mixture Models & EM. Nicholas Ruozzi University of Texas at Dallas. based on the slides of Vibhav Gogate

Mixture Models & EM. Nicholas Ruozzi University of Texas at Dallas. based on the slides of Vibhav Gogate Mixture Models & EM icholas Ruozzi University of Texas at Dallas based on the slides of Vibhav Gogate Previously We looed at -means and hierarchical clustering as mechanisms for unsupervised learning -means

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

The Expectation Maximization or EM algorithm

The Expectation Maximization or EM algorithm The Expectation Maximization or EM algorithm Carl Edward Rasmussen November 15th, 2017 Carl Edward Rasmussen The EM algorithm November 15th, 2017 1 / 11 Contents notation, objective the lower bound functional,

More information

Exponential Family and Maximum Likelihood, Gaussian Mixture Models and the EM Algorithm. by Korbinian Schwinger

Exponential Family and Maximum Likelihood, Gaussian Mixture Models and the EM Algorithm. by Korbinian Schwinger Exponential Family and Maximum Likelihood, Gaussian Mixture Models and the EM Algorithm by Korbinian Schwinger Overview Exponential Family Maximum Likelihood The EM Algorithm Gaussian Mixture Models Exponential

More information

Statistical Pattern Recognition

Statistical Pattern Recognition Statistical Pattern Recognition Expectation Maximization (EM) and Mixture Models Hamid R. Rabiee Jafar Muhammadi, Mohammad J. Hosseini Spring 2014 http://ce.sharif.edu/courses/92-93/2/ce725-2 Agenda Expectation-maximization

More information

Introduction to Machine Learning. Maximum Likelihood and Bayesian Inference. Lecturers: Eran Halperin, Lior Wolf

Introduction to Machine Learning. Maximum Likelihood and Bayesian Inference. Lecturers: Eran Halperin, Lior Wolf 1 Introduction to Machine Learning Maximum Likelihood and Bayesian Inference Lecturers: Eran Halperin, Lior Wolf 2014-15 We know that X ~ B(n,p), but we do not know p. We get a random sample from X, a

More information

Computing the MLE and the EM Algorithm

Computing the MLE and the EM Algorithm ECE 830 Fall 0 Statistical Signal Processing instructor: R. Nowak Computing the MLE and the EM Algorithm If X p(x θ), θ Θ, then the MLE is the solution to the equations logp(x θ) θ 0. Sometimes these equations

More information

Basic math for biology

Basic math for biology Basic math for biology Lei Li Florida State University, Feb 6, 2002 The EM algorithm: setup Parametric models: {P θ }. Data: full data (Y, X); partial data Y. Missing data: X. Likelihood and maximum likelihood

More information

STATS 306B: Unsupervised Learning Spring Lecture 3 April 7th

STATS 306B: Unsupervised Learning Spring Lecture 3 April 7th STATS 306B: Unsupervised Learning Spring 2014 Lecture 3 April 7th Lecturer: Lester Mackey Scribe: Jordan Bryan, Dangna Li 3.1 Recap: Gaussian Mixture Modeling In the last lecture, we discussed the Gaussian

More information

Outline. 1. Define likelihood 2. Interpretations of likelihoods 3. Likelihood plots 4. Maximum likelihood 5. Likelihood ratio benchmarks

Outline. 1. Define likelihood 2. Interpretations of likelihoods 3. Likelihood plots 4. Maximum likelihood 5. Likelihood ratio benchmarks Outline 1. Define likelihood 2. Interpretations of likelihoods 3. Likelihood plots 4. Maximum likelihood 5. Likelihood ratio benchmarks Likelihood A common and fruitful approach to statistics is to assume

More information

A Note on the Expectation-Maximization (EM) Algorithm

A Note on the Expectation-Maximization (EM) Algorithm A Note on the Expectation-Maximization (EM) Algorithm ChengXiang Zhai Department of Computer Science University of Illinois at Urbana-Champaign March 11, 2007 1 Introduction The Expectation-Maximization

More information

Parametric Unsupervised Learning Expectation Maximization (EM) Lecture 20.a

Parametric Unsupervised Learning Expectation Maximization (EM) Lecture 20.a Parametric Unsupervised Learning Expectation Maximization (EM) Lecture 20.a Some slides are due to Christopher Bishop Limitations of K-means Hard assignments of data points to clusters small shift of a

More information

Expectation maximization tutorial

Expectation maximization tutorial Expectation maximization tutorial Octavian Ganea November 18, 2016 1/1 Today Expectation - maximization algorithm Topic modelling 2/1 ML & MAP Observed data: X = {x 1, x 2... x N } 3/1 ML & MAP Observed

More information

Latent Variable Models and EM algorithm

Latent Variable Models and EM algorithm Latent Variable Models and EM algorithm SC4/SM4 Data Mining and Machine Learning, Hilary Term 2017 Dino Sejdinovic 3.1 Clustering and Mixture Modelling K-means and hierarchical clustering are non-probabilistic

More information

Review of Maximum Likelihood Estimators

Review of Maximum Likelihood Estimators Libby MacKinnon CSE 527 notes Lecture 7, October 7, 2007 MLE and EM Review of Maximum Likelihood Estimators MLE is one of many approaches to parameter estimation. The likelihood of independent observations

More information

Naïve Bayes classification

Naïve Bayes classification Naïve Bayes classification 1 Probability theory Random variable: a variable whose possible values are numerical outcomes of a random phenomenon. Examples: A person s height, the outcome of a coin toss

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

Weighted Finite-State Transducers in Computational Biology

Weighted Finite-State Transducers in Computational Biology Weighted Finite-State Transducers in Computational Biology Mehryar Mohri Courant Institute of Mathematical Sciences mohri@cims.nyu.edu Joint work with Corinna Cortes (Google Research). 1 This Tutorial

More information

Statistical learning. Chapter 20, Sections 1 4 1

Statistical learning. Chapter 20, Sections 1 4 1 Statistical learning Chapter 20, Sections 1 4 Chapter 20, Sections 1 4 1 Outline Bayesian learning Maximum a posteriori and maximum likelihood learning Bayes net learning ML parameter learning with complete

More information

Introduction to Machine Learning. Maximum Likelihood and Bayesian Inference. Lecturers: Eran Halperin, Yishay Mansour, Lior Wolf

Introduction to Machine Learning. Maximum Likelihood and Bayesian Inference. Lecturers: Eran Halperin, Yishay Mansour, Lior Wolf 1 Introduction to Machine Learning Maximum Likelihood and Bayesian Inference Lecturers: Eran Halperin, Yishay Mansour, Lior Wolf 2013-14 We know that X ~ B(n,p), but we do not know p. We get a random sample

More information

Clustering K-means. Clustering images. Machine Learning CSE546 Carlos Guestrin University of Washington. November 4, 2014.

Clustering K-means. Clustering images. Machine Learning CSE546 Carlos Guestrin University of Washington. November 4, 2014. Clustering K-means Machine Learning CSE546 Carlos Guestrin University of Washington November 4, 2014 1 Clustering images Set of Images [Goldberger et al.] 2 1 K-means Randomly initialize k centers µ (0)

More information

The Expectation-Maximization Algorithm

The Expectation-Maximization Algorithm 1/29 EM & Latent Variable Models Gaussian Mixture Models EM Theory The Expectation-Maximization Algorithm Mihaela van der Schaar Department of Engineering Science University of Oxford MLE for Latent Variable

More information

Lecture 8: Graphical models for Text

Lecture 8: Graphical models for Text Lecture 8: Graphical models for Text 4F13: Machine Learning Joaquin Quiñonero-Candela and Carl Edward Rasmussen Department of Engineering University of Cambridge http://mlg.eng.cam.ac.uk/teaching/4f13/

More information

Lecture 4 September 15

Lecture 4 September 15 IFT 6269: Probabilistic Graphical Models Fall 2017 Lecture 4 September 15 Lecturer: Simon Lacoste-Julien Scribe: Philippe Brouillard & Tristan Deleu 4.1 Maximum Likelihood principle Given a parametric

More information

Parametric Models: from data to models

Parametric Models: from data to models Parametric Models: from data to models Pradeep Ravikumar Co-instructor: Manuela Veloso Machine Learning 10-701 Jan 22, 2018 Recall: Model-based ML DATA MODEL LEARNING MODEL MODEL INFERENCE KNOWLEDGE Learning:

More information

IEOR E4570: Machine Learning for OR&FE Spring 2015 c 2015 by Martin Haugh. The EM Algorithm

IEOR E4570: Machine Learning for OR&FE Spring 2015 c 2015 by Martin Haugh. The EM Algorithm IEOR E4570: Machine Learning for OR&FE Spring 205 c 205 by Martin Haugh The EM Algorithm The EM algorithm is used for obtaining maximum likelihood estimates of parameters when some of the data is missing.

More information

Joint Optimization of Segmentation and Appearance Models

Joint Optimization of Segmentation and Appearance Models Joint Optimization of Segmentation and Appearance Models David Mandle, Sameep Tandon April 29, 2013 David Mandle, Sameep Tandon (Stanford) April 29, 2013 1 / 19 Overview 1 Recap: Image Segmentation 2 Optimization

More information

Naïve Bayes classification. p ij 11/15/16. Probability theory. Probability theory. Probability theory. X P (X = x i )=1 i. Marginal Probability

Naïve Bayes classification. p ij 11/15/16. Probability theory. Probability theory. Probability theory. X P (X = x i )=1 i. Marginal Probability Probability theory Naïve Bayes classification Random variable: a variable whose possible values are numerical outcomes of a random phenomenon. s: A person s height, the outcome of a coin toss Distinguish

More information

COM336: Neural Computing

COM336: Neural Computing COM336: Neural Computing http://www.dcs.shef.ac.uk/ sjr/com336/ Lecture 2: Density Estimation Steve Renals Department of Computer Science University of Sheffield Sheffield S1 4DP UK email: s.renals@dcs.shef.ac.uk

More information

Machine Learning for Data Science (CS4786) Lecture 12

Machine Learning for Data Science (CS4786) Lecture 12 Machine Learning for Data Science (CS4786) Lecture 12 Gaussian Mixture Models Course Webpage : http://www.cs.cornell.edu/courses/cs4786/2016fa/ Back to K-means Single link is sensitive to outliners We

More information

Machine Learning. Gaussian Mixture Models. Zhiyao Duan & Bryan Pardo, Machine Learning: EECS 349 Fall

Machine Learning. Gaussian Mixture Models. Zhiyao Duan & Bryan Pardo, Machine Learning: EECS 349 Fall Machine Learning Gaussian Mixture Models Zhiyao Duan & Bryan Pardo, Machine Learning: EECS 349 Fall 2012 1 The Generative Model POV We think of the data as being generated from some process. We assume

More information

Expectation Maximization and Mixtures of Gaussians

Expectation Maximization and Mixtures of Gaussians Statistical Machine Learning Notes 10 Expectation Maximiation and Mixtures of Gaussians Instructor: Justin Domke Contents 1 Introduction 1 2 Preliminary: Jensen s Inequality 2 3 Expectation Maximiation

More information

Week 3: The EM algorithm

Week 3: The EM algorithm Week 3: The EM algorithm Maneesh Sahani maneesh@gatsby.ucl.ac.uk Gatsby Computational Neuroscience Unit University College London Term 1, Autumn 2005 Mixtures of Gaussians Data: Y = {y 1... y N } Latent

More information

Expectation Maximization

Expectation Maximization Expectation Maximization Seungjin Choi Department of Computer Science and Engineering Pohang University of Science and Technology 77 Cheongam-ro, Nam-gu, Pohang 37673, Korea seungjin@postech.ac.kr 1 /

More information

Expectation Maximization

Expectation Maximization Expectation Maximization Bishop PRML Ch. 9 Alireza Ghane c Ghane/Mori 4 6 8 4 6 8 4 6 8 4 6 8 5 5 5 5 5 5 4 6 8 4 4 6 8 4 5 5 5 5 5 5 µ, Σ) α f Learningscale is slightly Parameters is slightly larger larger

More information

Expectation Maximization Algorithm

Expectation Maximization Algorithm Expectation Maximization Algorithm Vibhav Gogate The University of Texas at Dallas Slides adapted from Carlos Guestrin, Dan Klein, Luke Zettlemoyer and Dan Weld The Evils of Hard Assignments? Clusters

More information

Expectation Maximization

Expectation Maximization Expectation Maximization Aaron C. Courville Université de Montréal Note: Material for the slides is taken directly from a presentation prepared by Christopher M. Bishop Learning in DAGs Two things could

More information

COMP90051 Statistical Machine Learning

COMP90051 Statistical Machine Learning COMP90051 Statistical Machine Learning Semester 2, 2017 Lecturer: Trevor Cohn 2. Statistical Schools Adapted from slides by Ben Rubinstein Statistical Schools of Thought Remainder of lecture is to provide

More information

Quick Tour of Basic Probability Theory and Linear Algebra

Quick Tour of Basic Probability Theory and Linear Algebra Quick Tour of and Linear Algebra Quick Tour of and Linear Algebra CS224w: Social and Information Network Analysis Fall 2011 Quick Tour of and Linear Algebra Quick Tour of and Linear Algebra Outline Definitions

More information

Gaussian Mixture Models, Expectation Maximization

Gaussian Mixture Models, Expectation Maximization Gaussian Mixture Models, Expectation Maximization Instructor: Jessica Wu Harvey Mudd College The instructor gratefully acknowledges Andrew Ng (Stanford), Andrew Moore (CMU), Eric Eaton (UPenn), David Kauchak

More information

Latent Variable Models

Latent Variable Models Latent Variable Models Stefano Ermon, Aditya Grover Stanford University Lecture 5 Stefano Ermon, Aditya Grover (AI Lab) Deep Generative Models Lecture 5 1 / 31 Recap of last lecture 1 Autoregressive models:

More information

Performance Comparison of K-Means and Expectation Maximization with Gaussian Mixture Models for Clustering EE6540 Final Project

Performance Comparison of K-Means and Expectation Maximization with Gaussian Mixture Models for Clustering EE6540 Final Project Performance Comparison of K-Means and Expectation Maximization with Gaussian Mixture Models for Clustering EE6540 Final Project Devin Cornell & Sushruth Sastry May 2015 1 Abstract In this article, we explore

More information

Computer Intensive Methods in Mathematical Statistics

Computer Intensive Methods in Mathematical Statistics Computer Intensive Methods in Mathematical Statistics Department of mathematics johawes@kth.se Lecture 16 Advanced topics in computational statistics 18 May 2017 Computer Intensive Methods (1) Plan of

More information

SYDE 372 Introduction to Pattern Recognition. Probability Measures for Classification: Part I

SYDE 372 Introduction to Pattern Recognition. Probability Measures for Classification: Part I SYDE 372 Introduction to Pattern Recognition Probability Measures for Classification: Part I Alexander Wong Department of Systems Design Engineering University of Waterloo Outline 1 2 3 4 Why use probability

More information

Outline. 1. Define likelihood 2. Interpretations of likelihoods 3. Likelihood plots 4. Maximum likelihood 5. Likelihood ratio benchmarks

Outline. 1. Define likelihood 2. Interpretations of likelihoods 3. Likelihood plots 4. Maximum likelihood 5. Likelihood ratio benchmarks This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike License. Your use of this material constitutes acceptance of that license and the conditions of use of materials on this

More information

6.867 Machine Learning

6.867 Machine Learning 6.867 Machine Learning Problem set 1 Solutions Thursday, September 19 What and how to turn in? Turn in short written answers to the questions explicitly stated, and when requested to explain or prove.

More information

Pattern Recognition and Machine Learning. Bishop Chapter 9: Mixture Models and EM

Pattern Recognition and Machine Learning. Bishop Chapter 9: Mixture Models and EM Pattern Recognition and Machine Learning Chapter 9: Mixture Models and EM Thomas Mensink Jakob Verbeek October 11, 27 Le Menu 9.1 K-means clustering Getting the idea with a simple example 9.2 Mixtures

More information

Speech Recognition Lecture 8: Expectation-Maximization Algorithm, Hidden Markov Models.

Speech Recognition Lecture 8: Expectation-Maximization Algorithm, Hidden Markov Models. Speech Recognition Lecture 8: Expectation-Maximization Algorithm, Hidden Markov Models. Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.com This Lecture Expectation-Maximization (EM)

More information

6.867 Machine Learning

6.867 Machine Learning 6.867 Machine Learning Problem set 1 Due Thursday, September 19, in class What and how to turn in? Turn in short written answers to the questions explicitly stated, and when requested to explain or prove.

More information

1 Expectation Maximization

1 Expectation Maximization Introduction Expectation-Maximization Bibliographical notes 1 Expectation Maximization Daniel Khashabi 1 khashab2@illinois.edu 1.1 Introduction Consider the problem of parameter learning by maximizing

More information

Bayesian Interpretations of Regularization

Bayesian Interpretations of Regularization Bayesian Interpretations of Regularization Charlie Frogner 9.50 Class 15 April 1, 009 The Plan Regularized least squares maps {(x i, y i )} n i=1 to a function that minimizes the regularized loss: f S

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

Introduction to Machine Learning

Introduction to Machine Learning Introduction to Machine Learning Brown University CSCI 1950-F, Spring 2012 Prof. Erik Sudderth Lecture 20: Expectation Maximization Algorithm EM for Mixture Models Many figures courtesy Kevin Murphy s

More information

Lecture 4: Hidden Markov Models: An Introduction to Dynamic Decision Making. November 11, 2010

Lecture 4: Hidden Markov Models: An Introduction to Dynamic Decision Making. November 11, 2010 Hidden Lecture 4: Hidden : An Introduction to Dynamic Decision Making November 11, 2010 Special Meeting 1/26 Markov Model Hidden When a dynamical system is probabilistic it may be determined by the transition

More information

9/12/17. Types of learning. Modeling data. Supervised learning: Classification. Supervised learning: Regression. Unsupervised learning: Clustering

9/12/17. Types of learning. Modeling data. Supervised learning: Classification. Supervised learning: Regression. Unsupervised learning: Clustering Types of learning Modeling data Supervised: we know input and targets Goal is to learn a model that, given input data, accurately predicts target data Unsupervised: we know the input only and want to make

More information

6.864: Lecture 5 (September 22nd, 2005) The EM Algorithm

6.864: Lecture 5 (September 22nd, 2005) The EM Algorithm 6.864: Lecture 5 (September 22nd, 2005) The EM Algorithm Overview The EM algorithm in general form The EM algorithm for hidden markov models (brute force) The EM algorithm for hidden markov models (dynamic

More information

Lecture 3 September 1

Lecture 3 September 1 STAT 383C: Statistical Modeling I Fall 2016 Lecture 3 September 1 Lecturer: Purnamrita Sarkar Scribe: Giorgio Paulon, Carlos Zanini Disclaimer: These scribe notes have been slightly proofread and may have

More information

Lecture 6: April 19, 2002

Lecture 6: April 19, 2002 EE596 Pat. Recog. II: Introduction to Graphical Models Spring 2002 Lecturer: Jeff Bilmes Lecture 6: April 19, 2002 University of Washington Dept. of Electrical Engineering Scribe: Huaning Niu,Özgür Çetin

More information

Series 6, May 14th, 2018 (EM Algorithm and Semi-Supervised Learning)

Series 6, May 14th, 2018 (EM Algorithm and Semi-Supervised Learning) Exercises Introduction to Machine Learning SS 2018 Series 6, May 14th, 2018 (EM Algorithm and Semi-Supervised Learning) LAS Group, Institute for Machine Learning Dept of Computer Science, ETH Zürich Prof

More information

Maximum Likelihood Estimation. only training data is available to design a classifier

Maximum Likelihood Estimation. only training data is available to design a classifier Introduction to Pattern Recognition [ Part 5 ] Mahdi Vasighi Introduction Bayesian Decision Theory shows that we could design an optimal classifier if we knew: P( i ) : priors p(x i ) : class-conditional

More information

EECS E6870: Lecture 4: Hidden Markov Models

EECS E6870: Lecture 4: Hidden Markov Models EECS E6870: Lecture 4: Hidden Markov Models Stanley F. Chen, Michael A. Picheny and Bhuvana Ramabhadran IBM T. J. Watson Research Center Yorktown Heights, NY 10549 stanchen@us.ibm.com, picheny@us.ibm.com,

More information

Statistics: Learning models from data

Statistics: Learning models from data DS-GA 1002 Lecture notes 5 October 19, 2015 Statistics: Learning models from data Learning models from data that are assumed to be generated probabilistically from a certain unknown distribution is a crucial

More information

Basics on Probability. Jingrui He 09/11/2007

Basics on Probability. Jingrui He 09/11/2007 Basics on Probability Jingrui He 09/11/2007 Coin Flips You flip a coin Head with probability 0.5 You flip 100 coins How many heads would you expect Coin Flips cont. You flip a coin Head with probability

More information

Lecture 14. Clustering, K-means, and EM

Lecture 14. Clustering, K-means, and EM Lecture 14. Clustering, K-means, and EM Prof. Alan Yuille Spring 2014 Outline 1. Clustering 2. K-means 3. EM 1 Clustering Task: Given a set of unlabeled data D = {x 1,..., x n }, we do the following: 1.

More information

Notes on Machine Learning for and

Notes on Machine Learning for and Notes on Machine Learning for 16.410 and 16.413 (Notes adapted from Tom Mitchell and Andrew Moore.) Choosing Hypotheses Generally want the most probable hypothesis given the training data Maximum a posteriori

More information

Fundamentals. CS 281A: Statistical Learning Theory. Yangqing Jia. August, Based on tutorial slides by Lester Mackey and Ariel Kleiner

Fundamentals. CS 281A: Statistical Learning Theory. Yangqing Jia. August, Based on tutorial slides by Lester Mackey and Ariel Kleiner Fundamentals CS 281A: Statistical Learning Theory Yangqing Jia Based on tutorial slides by Lester Mackey and Ariel Kleiner August, 2011 Outline 1 Probability 2 Statistics 3 Linear Algebra 4 Optimization

More information

f X (y, z; θ, σ 2 ) = 1 2 (2πσ2 ) 1 2 exp( (y θz) 2 /2σ 2 ) l c,n (θ, σ 2 ) = i log f(y i, Z i ; θ, σ 2 ) (Y i θz i ) 2 /2σ 2

f X (y, z; θ, σ 2 ) = 1 2 (2πσ2 ) 1 2 exp( (y θz) 2 /2σ 2 ) l c,n (θ, σ 2 ) = i log f(y i, Z i ; θ, σ 2 ) (Y i θz i ) 2 /2σ 2 Chapter 7: EM algorithm in exponential families: JAW 4.30-32 7.1 (i) The EM Algorithm finds MLE s in problems with latent variables (sometimes called missing data ): things you wish you could observe,

More information

Review of probabilities

Review of probabilities CS 1675 Introduction to Machine Learning Lecture 5 Density estimation Milos Hauskrecht milos@pitt.edu 5329 Sennott Square Review of probabilities 1 robability theory Studies and describes random processes

More information

Computational Statistics. Jian Pei School of Computing Science Simon Fraser University

Computational Statistics. Jian Pei School of Computing Science Simon Fraser University Computational Statistics Jian Pei School of Computing Science Simon Fraser University jpei@cs.sfu.ca BASIC OPTIMIZATION METHODS J. Pei: Computational Statistics 2 Why Optimization? In statistical inference,

More information

CS Lecture 18. Expectation Maximization

CS Lecture 18. Expectation Maximization CS 6347 Lecture 18 Expectation Maximization Unobserved Variables Latent or hidden variables in the model are never observed We may or may not be interested in their values, but their existence is crucial

More information

Machine Learning for Signal Processing Expectation Maximization Mixture Models. Bhiksha Raj 27 Oct /

Machine Learning for Signal Processing Expectation Maximization Mixture Models. Bhiksha Raj 27 Oct / Machine Learning for Signal rocessing Expectation Maximization Mixture Models Bhiksha Raj 27 Oct 2016 11755/18797 1 Learning Distributions for Data roblem: Given a collection of examples from some data,

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

Statistics 3858 : Maximum Likelihood Estimators

Statistics 3858 : Maximum Likelihood Estimators Statistics 3858 : Maximum Likelihood Estimators 1 Method of Maximum Likelihood In this method we construct the so called likelihood function, that is L(θ) = L(θ; X 1, X 2,..., X n ) = f n (X 1, X 2,...,

More information

EM Algorithm. Expectation-maximization (EM) algorithm.

EM Algorithm. Expectation-maximization (EM) algorithm. EM Algorithm Outline: Expectation-maximization (EM) algorithm. Examples. Reading: A.P. Dempster, N.M. Laird, and D.B. Rubin, Maximum likelihood from incomplete data via the EM algorithm, J. R. Stat. Soc.,

More information

Review and Motivation

Review and Motivation Review and Motivation We can model and visualize multimodal datasets by using multiple unimodal (Gaussian-like) clusters. K-means gives us a way of partitioning points into N clusters. Once we know which

More information

ON SOME TWO-STEP DENSITY ESTIMATION METHOD

ON SOME TWO-STEP DENSITY ESTIMATION METHOD UNIVESITATIS IAGELLONICAE ACTA MATHEMATICA, FASCICULUS XLIII 2005 ON SOME TWO-STEP DENSITY ESTIMATION METHOD by Jolanta Jarnicka Abstract. We introduce a new two-step kernel density estimation method,

More information

Clustering with k-means and Gaussian mixture distributions

Clustering with k-means and Gaussian mixture distributions Clustering with k-means and Gaussian mixture distributions Machine Learning and Category Representation 2014-2015 Jakob Verbeek, ovember 21, 2014 Course website: http://lear.inrialpes.fr/~verbeek/mlcr.14.15

More information

Maximum likelihood estimation

Maximum likelihood estimation Maximum likelihood estimation Guillaume Obozinski Ecole des Ponts - ParisTech Master MVA Maximum likelihood estimation 1/26 Outline 1 Statistical concepts 2 A short review of convex analysis and optimization

More information

Variables which are always unobserved are called latent variables or sometimes hidden variables. e.g. given y,x fit the model p(y x) = z p(y x,z)p(z)

Variables which are always unobserved are called latent variables or sometimes hidden variables. e.g. given y,x fit the model p(y x) = z p(y x,z)p(z) CSC2515 Machine Learning Sam Roweis Lecture 8: Unsupervised Learning & EM Algorithm October 31, 2006 Partially Unobserved Variables 2 Certain variables q in our models may be unobserved, either at training

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

A brief introduction to Conditional Random Fields

A brief introduction to Conditional Random Fields A brief introduction to Conditional Random Fields Mark Johnson Macquarie University April, 2005, updated October 2010 1 Talk outline Graphical models Maximum likelihood and maximum conditional likelihood

More information

Ph.D. Qualifying Exam Friday Saturday, January 6 7, 2017

Ph.D. Qualifying Exam Friday Saturday, January 6 7, 2017 Ph.D. Qualifying Exam Friday Saturday, January 6 7, 2017 Put your solution to each problem on a separate sheet of paper. Problem 1. (5106) Let X 1, X 2,, X n be a sequence of i.i.d. observations from a

More information

Parameter Estimation. Industrial AI Lab.

Parameter Estimation. Industrial AI Lab. Parameter Estimation Industrial AI Lab. Generative Model X Y w y = ω T x + ε ε~n(0, σ 2 ) σ 2 2 Maximum Likelihood Estimation (MLE) Estimate parameters θ ω, σ 2 given a generative model Given observed

More information

COMS 4721: Machine Learning for Data Science Lecture 16, 3/28/2017

COMS 4721: Machine Learning for Data Science Lecture 16, 3/28/2017 COMS 4721: Machine Learning for Data Science Lecture 16, 3/28/2017 Prof. John Paisley Department of Electrical Engineering & Data Science Institute Columbia University SOFT CLUSTERING VS HARD CLUSTERING

More information

Mixture Models and Expectation-Maximization

Mixture Models and Expectation-Maximization Mixture Models and Expectation-Maximiation David M. Blei March 9, 2012 EM for mixtures of multinomials The graphical model for a mixture of multinomials π d x dn N D θ k K How should we fit the parameters?

More information

Finite Mixture Models and Clustering

Finite Mixture Models and Clustering Finite Mixture Models and Clustering Mohamed Nadif LIPADE, Université Paris Descartes, France Nadif (LIPADE) EPAT, May, 2010 Course 3 1 / 40 Introduction Outline 1 Introduction Mixture Approach 2 Finite

More information

Lecture 4: Probabilistic Learning. Estimation Theory. Classification with Probability Distributions

Lecture 4: Probabilistic Learning. Estimation Theory. Classification with Probability Distributions DD2431 Autumn, 2014 1 2 3 Classification with Probability Distributions Estimation Theory Classification in the last lecture we assumed we new: P(y) Prior P(x y) Lielihood x2 x features y {ω 1,..., ω K

More information

Parametric Models. Dr. Shuang LIANG. School of Software Engineering TongJi University Fall, 2012

Parametric Models. Dr. Shuang LIANG. School of Software Engineering TongJi University Fall, 2012 Parametric Models Dr. Shuang LIANG School of Software Engineering TongJi University Fall, 2012 Today s Topics Maximum Likelihood Estimation Bayesian Density Estimation Today s Topics Maximum Likelihood

More information

Variable selection for model-based clustering

Variable selection for model-based clustering Variable selection for model-based clustering Matthieu Marbac (Ensai - Crest) Joint works with: M. Sedki (Univ. Paris-sud) and V. Vandewalle (Univ. Lille 2) The problem Objective: Estimation of a partition

More information

Introduction to Maximum Likelihood Estimation

Introduction to Maximum Likelihood Estimation Introduction to Maximum Likelihood Estimation Eric Zivot July 26, 2012 The Likelihood Function Let 1 be an iid sample with pdf ( ; ) where is a ( 1) vector of parameters that characterize ( ; ) Example:

More information

DS-GA 1002 Lecture notes 11 Fall Bayesian statistics

DS-GA 1002 Lecture notes 11 Fall Bayesian statistics DS-GA 100 Lecture notes 11 Fall 016 Bayesian statistics In the frequentist paradigm we model the data as realizations from a distribution that depends on deterministic parameters. In contrast, in Bayesian

More information

Statistics - Lecture One. Outline. Charlotte Wickham 1. Basic ideas about estimation

Statistics - Lecture One. Outline. Charlotte Wickham  1. Basic ideas about estimation Statistics - Lecture One Charlotte Wickham wickham@stat.berkeley.edu http://www.stat.berkeley.edu/~wickham/ Outline 1. Basic ideas about estimation 2. Method of Moments 3. Maximum Likelihood 4. Confidence

More information

Review: Probability. BM1: Advanced Natural Language Processing. University of Potsdam. Tatjana Scheffler

Review: Probability. BM1: Advanced Natural Language Processing. University of Potsdam. Tatjana Scheffler Review: Probability BM1: Advanced Natural Language Processing University of Potsdam Tatjana Scheffler tatjana.scheffler@uni-potsdam.de October 21, 2016 Today probability random variables Bayes rule expectation

More information

CSC321 Lecture 18: Learning Probabilistic Models

CSC321 Lecture 18: Learning Probabilistic Models CSC321 Lecture 18: Learning Probabilistic Models Roger Grosse Roger Grosse CSC321 Lecture 18: Learning Probabilistic Models 1 / 25 Overview So far in this course: mainly supervised learning Language modeling

More information

Lecture 15. Probabilistic Models on Graph

Lecture 15. Probabilistic Models on Graph Lecture 15. Probabilistic Models on Graph Prof. Alan Yuille Spring 2014 1 Introduction We discuss how to define probabilistic models that use richly structured probability distributions and describe how

More information

Finite Singular Multivariate Gaussian Mixture

Finite Singular Multivariate Gaussian Mixture 21/06/2016 Plan 1 Basic definitions Singular Multivariate Normal Distribution 2 3 Plan Singular Multivariate Normal Distribution 1 Basic definitions Singular Multivariate Normal Distribution 2 3 Multivariate

More information