Efficient Iterative Semi-supervised Classification on Manifold

Size: px
Start display at page:

Download "Efficient Iterative Semi-supervised Classification on Manifold"

Transcription

1 . Efficient Iterative Semi-supervised Classification on Manifold... M. Farajtabar, H. R. Rabiee, A. Shaban, A. Soltani-Farani Sharif University of Technology, Tehran, Iran. Presented by Pooria Joulani University of Alberta December 11, 2011 M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

2 ...1 Introduction Graph Transduction...2 The Algorithm Analysis...3 The Algorithm Analysis...4 Setup Scenarios Summary and Future Works M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

3 . Semi-supervised Learning Introduction Graph Transduction Semi-supervised Learning: utilize unlabeled data to to enhance classification Manifold assumption: the labeling function varies smoothly with respect to the underlying manifold Manifold structure is modeled by the neighborhood graph of the data points Application such as image segmentation, handwritten digit recognition, text classification, and etc SSL is advantageous when there is large amount of unlabeled data which leads to better utilization of the underlying geometry Large-scale setting; time and memory limitation Efficient implementation M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

4 . Graph Transduction Algorithms Introduction Graph Transduction Graph Transduction: a simple form of manifold regularization algorithms Can be formulated as: arg min x where A R n n and b, x R n 1 2 x T Ax b T x, (1) Equivalent to solving the system of linear equations, Ax = b A is fortunately a sparse symmetric positive definite matrix M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

5 . Naive Solutions Outline Introduction Graph Transduction Require O(n 3 ) operations Methods that take into account the sparse structure of A can cost much less Taking the inverse of A directly is an obvious bad choice for various reasons Requires O(n 3 ) operations regardless of the sparsity A may be near singular in which case the inverse operation is numerically unstable The inverse of A is usually not sparse in which case a large amount of memory is needed to store and process A 1. M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

6 . Two Approaches Introduction Graph Transduction Reformulate the manifold regularization problem Linear kernel Sparsified regularizer Solve the original formulation via Factorization methods LQ LU Cholesky Optimization algorithms Gradient descent Conjugate gradient Quasi Newton Iterative methods LP LGC LNP M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

7 . Problem Statement Introduction Graph Transduction Let X u = {x 1,..., x u } and X l = {x u+1,..., x u+l } be sets of unlabeled and labeled data points, respectively, where n = u + l Let y be a vector of length n with y i = 0 for unlabeled x i and y i equals to the 1 or 1 corresponding to the class labels Our goal is to predict labels of X = X u X l as f Let W be the weight matrix of the k-nn graph of X, where σ is the bandwidth parameter W (i, j) = exp( x i x j 2 /2σ) (2) M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

8 . Problem Statement (cont.) Introduction Graph Transduction The family of graph transduction algorithms can be formulated as the following optimization problem: arg min f T Qf + (f y) T C(f y) (3) f where Q is a regularization matrix and C is a diagonal matrix with C ii equal to the importance of the i th node to stick to y i The first term represents smoothness of the predicted labels with respect to the underlying manifold The second term is squared error of the predicted labels compared with the initial ones weighted by C. Choosing different Qs and Cs leads to various manifold classification methods: Thikhonv Regularization Label Propagation and Harmonic Solution Local and Global Consistency M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

9 . Problem Statement (cont.) Introduction Graph Transduction Defining diagonal matrix D with D(i, i) = n j=1 W (i, j), symmetrically normalize W by S = D 1/2 WD 1/2. The Laplacian matrix is L = I S In Local and Global Consistency (LGC), Q = L and C = µi, i.e. we want to minimize R(f ) = f T Lf + (f y) T C(f y). (4) It may easily be shown that the solution is equal to: f = (L + C) 1 Cy = (I αs) 1 y, (5) where α = 1 µ+1 An iterative algorithm to compute this solution: f (t+1) = αsf (t) + (1 α)y. (6) M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

10 . Gradient descent The Algorithm Analysis Gradient of the objective function is R = 2(Lf + C(f y)), Gradient descent update rule: f (t+1) = f (t) 2α(Lf + C(f y))). (7) The stopping criterion is R η. Choosing α appropriately is essential for convergence Applying exact line search at iteration t: t log ( R (0) R log (1/z) R (t) R ) which z is a constant equal to 1 λ min(l+c) λ max (L+C).. (8) M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

11 . Gradient Descent (cont.) The Algorithm Analysis. Theorem 1.. The maximum number of iterations for gradient descent with exact line. search and fixed (η, µ) is O(log n)... To be exact: t (2+µ) log ( 2 n η ) 2 log (1 + µ 2 ). (9) Each iteration costs a sparse matrix-vector multiplication plus vector sums O(n) for each iteration given neighborhood size, k, is constant and small An O(n log n) rate of growth with respect the number of data, n The bound is valid for other graph transduction algorithms M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

12 . Newton s algorithm The Algorithm Analysis Newton s update rule for our problem is approximating the inverse Hessian. f (t+1) = f (t) α( 2 R) 1 R (10) ( 2 R) 1 = 1 2 (L + C) 1 = 1 (I S + C) 1 2 = 1 ( I (I + C) 1 S ) 1 (I + C) 1 (11) 2 = 1 ( Σ ( i=0 (I + C) 1 S ) ) i (I + C) 1 2 Using the m first terms in the above summation leads to an approximation of the inverse Hessian: ( ( 2 R) 1 ( (I + C) 1 S ) ) i (I + C) 1. (12) Σ m 1 i=0 M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

13 . Approximate Newton s algorithm The Algorithm Analysis Rewriting Newton s method with the approximated inverse Hessian and doing some math: where f (t+1) = H m f (t) + g m, (13) H = (I + C) 1 S (14) m 1 g m = ( H i )(I + C) 1 Cy. (15) i=0 This update rule is performed iteratively from an initial f (0) until the stopping criterion R η is reached. LGC s default iterative procedure is a especial case of the proposed method with m = 1. M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

14 . Analysis Outline The Algorithm Analysis. Theorem 2... The approximate Newton s method converges to the solution of LGC.... Theorem 3.. For the approximate Newton s method the stopping criterion R η is. reached in O(log n) iterations... To be exact: t log ( (2+µ)n η ) m log (1 + µ) (16) m is empirically set to 1,2, or 3. A larger m disturbs sparsity. Given neighborhood size, k, is constant and small, cost of each iteration is equal to a sparse matrix-vector multiplication, i.e., O(n). Given η and µ are constant, the time complexity is O(n log n). M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

15 . Illusteration Outline The Algorithm Analysis Optimization for two data points from MNIST Gradient descent Approx. Newton m = 1 Approx. Newton m = 2 Gradient Descent LGC (m = 1) Approximate method m = 2 Consider the directions which the methods find M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

16 Setup Scenarios Summary and Future Works data from two classes of MNIST; handwritten digit recognition data from two classes of Covertype; forest cover prediction 7000 data from Classic dataset; text categorization Comparison with CHOLMOD and LGC s default implementation 5-NN for neighborhood construction Bandwidth size set to mean of standard deviation of data 2 % of data points are labeled µ is set to 0.5 η = empirically ensures convergence to the optimal solutions Number of Iterations, accuracy, and distance to optimum are reported by average of 10 runs for different random labelings M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

17 . Number of iterations Setup Scenarios Summary and Future Works Number of Iterations 35 LGC Approx. Newton m = 2 30 Gradient Descent Number of data (a) MNIST Number of Iterations Number of data x 10 4 (b) Covertype 35 Number of Iterations Number of data (c) Classic M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

18 . Accuracy Outline Setup Scenarios Summary and Future Works Accuracy 1.05 LGC Approx. Newton m = 2 Gradient Descent 1 CHOLMOD 0.95 Accuracy Number of data (d) MNIST Number of data x 10 4 (e) Covertype Accuracy Number of data (f) Classic M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

19 . Distance form optimum Setup Scenarios Summary and Future Works f (t) f * 150 LGC Approx. Newton m = 2 Gradient Descent f (t) f * Number of iterations (g) MNIST Number of iterations (h) Covertype f (t) f * Number of iterations (i) Classic M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

20 . Time Outline Setup Scenarios Summary and Future Works Duration (Sec) 4Approx. Newton m = 2 CHOLMOD Duration (Sec) 0.08LGC Approx. Newton m = Gradient Descent Number of data (j) MNIST Number of data (k) MNIST M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

21 Setup Scenarios Summary and Future Works Summary A novel approximation to Newton s method is proposed for solving graph transduction problems A theoretical analysis on the number of iterations for the proposed method and the gradient descent method The number of iterations have logarithmic dependence on the number of data A reasonable approach when a large amount of data is being classified Future works: Analysis of robustness against noise Incorporating a low cost line search with the proposed method M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

22 Setup Scenarios Summary and Future Works Thanks for your Attention. M. Farajtabar et al. Efficient Iterative Semi-supervised Classification on Manifold December 11, / 22

(Sparse) Linear Solvers

(Sparse) Linear Solvers (Sparse) Linear Solvers Ax = B Why? Many geometry processing applications boil down to: solve one or more linear systems Parameterization Editing Reconstruction Fairing Morphing 2 Don t you just invert

More information

GRAPH-BASED SEMI-SUPERVISED HYPERSPECTRAL IMAGE CLASSIFICATION USING SPATIAL INFORMATION

GRAPH-BASED SEMI-SUPERVISED HYPERSPECTRAL IMAGE CLASSIFICATION USING SPATIAL INFORMATION GRAPH-BASED SEMI-SUPERVISED HYPERSPECTRAL IMAGE CLASSIFICATION USING SPATIAL INFORMATION Nasehe Jamshidpour a, Saeid Homayouni b, Abdolreza Safari a a Dept. of Geomatics Engineering, College of Engineering,

More information

Combine the PA Algorithm with a Proximal Classifier

Combine the PA Algorithm with a Proximal Classifier Combine the Passive and Aggressive Algorithm with a Proximal Classifier Yuh-Jye Lee Joint work with Y.-C. Tseng Dept. of Computer Science & Information Engineering TaiwanTech. Dept. of Statistics@NCKU

More information

(Sparse) Linear Solvers

(Sparse) Linear Solvers (Sparse) Linear Solvers Ax = B Why? Many geometry processing applications boil down to: solve one or more linear systems Parameterization Editing Reconstruction Fairing Morphing 1 Don t you just invert

More information

Thorsten Joachims Then: Universität Dortmund, Germany Now: Cornell University, USA

Thorsten Joachims Then: Universität Dortmund, Germany Now: Cornell University, USA Retrospective ICML99 Transductive Inference for Text Classification using Support Vector Machines Thorsten Joachims Then: Universität Dortmund, Germany Now: Cornell University, USA Outline The paper in

More information

Divide and Conquer Kernel Ridge Regression

Divide 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 information

Bipartite Edge Prediction via Transductive Learning over Product Graphs

Bipartite Edge Prediction via Transductive Learning over Product Graphs Bipartite Edge Prediction via Transductive Learning over Product Graphs Hanxiao Liu, Yiming Yang School of Computer Science, Carnegie Mellon University July 8, 2015 ICML 2015 Bipartite Edge Prediction

More information

Improving Image Segmentation Quality Via Graph Theory

Improving Image Segmentation Quality Via Graph Theory International Symposium on Computers & Informatics (ISCI 05) Improving Image Segmentation Quality Via Graph Theory Xiangxiang Li, Songhao Zhu School of Automatic, Nanjing University of Post and Telecommunications,

More information

MOST machine learning algorithms rely on the assumption

MOST machine learning algorithms rely on the assumption 1 Domain Adaptation on Graphs by Learning Aligned Graph Bases Mehmet Pilancı and Elif Vural arxiv:183.5288v1 [stat.ml] 14 Mar 218 Abstract We propose a method for domain adaptation on graphs. Given sufficiently

More information

Introduction to Optimization

Introduction to Optimization Introduction to Optimization Second Order Optimization Methods Marc Toussaint U Stuttgart Planned Outline Gradient-based optimization (1st order methods) plain grad., steepest descent, conjugate grad.,

More information

Large-Scale Lasso and Elastic-Net Regularized Generalized Linear Models

Large-Scale Lasso and Elastic-Net Regularized Generalized Linear Models Large-Scale Lasso and Elastic-Net Regularized Generalized Linear Models DB Tsai Steven Hillion Outline Introduction Linear / Nonlinear Classification Feature Engineering - Polynomial Expansion Big-data

More information

Convexization in Markov Chain Monte Carlo

Convexization in Markov Chain Monte Carlo in Markov Chain Monte Carlo 1 IBM T. J. Watson Yorktown Heights, NY 2 Department of Aerospace Engineering Technion, Israel August 23, 2011 Problem Statement MCMC processes in general are governed by non

More information

DS Machine Learning and Data Mining I. Alina Oprea Associate Professor, CCIS Northeastern University

DS Machine Learning and Data Mining I. Alina Oprea Associate Professor, CCIS Northeastern University DS 4400 Machine Learning and Data Mining I Alina Oprea Associate Professor, CCIS Northeastern University September 20 2018 Review Solution for multiple linear regression can be computed in closed form

More information

Graph Laplacian Kernels for Object Classification from a Single Example

Graph Laplacian Kernels for Object Classification from a Single Example Graph Laplacian Kernels for Object Classification from a Single Example Hong Chang & Dit-Yan Yeung Department of Computer Science, Hong Kong University of Science and Technology {hongch,dyyeung}@cs.ust.hk

More information

Classification: Linear Discriminant Functions

Classification: Linear Discriminant Functions Classification: Linear Discriminant Functions CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Discriminant functions Linear Discriminant functions

More information

Capturing, Modeling, Rendering 3D Structures

Capturing, Modeling, Rendering 3D Structures Computer Vision Approach Capturing, Modeling, Rendering 3D Structures Calculate pixel correspondences and extract geometry Not robust Difficult to acquire illumination effects, e.g. specular highlights

More information

Generalized trace ratio optimization and applications

Generalized trace ratio optimization and applications Generalized trace ratio optimization and applications Mohammed Bellalij, Saïd Hanafi, Rita Macedo and Raca Todosijevic University of Valenciennes, France PGMO Days, 2-4 October 2013 ENSTA ParisTech PGMO

More information

Contents. I Basics 1. Copyright by SIAM. Unauthorized reproduction of this article is prohibited.

Contents. I Basics 1. Copyright by SIAM. Unauthorized reproduction of this article is prohibited. page v Preface xiii I Basics 1 1 Optimization Models 3 1.1 Introduction... 3 1.2 Optimization: An Informal Introduction... 4 1.3 Linear Equations... 7 1.4 Linear Optimization... 10 Exercises... 12 1.5

More information

Learning Two-View Stereo Matching

Learning Two-View Stereo Matching Learning Two-View Stereo Matching Jianxiong Xiao Jingni Chen Dit-Yan Yeung Long Quan Department of Computer Science and Engineering The Hong Kong University of Science and Technology The 10th European

More information

Transductive Phoneme Classification Using Local Scaling And Confidence

Transductive Phoneme Classification Using Local Scaling And Confidence 202 IEEE 27-th Convention of Electrical and Electronics Engineers in Israel Transductive Phoneme Classification Using Local Scaling And Confidence Matan Orbach Dept. of Electrical Engineering Technion

More information

Alternating Minimization. Jun Wang, Tony Jebara, and Shih-fu Chang

Alternating Minimization. Jun Wang, Tony Jebara, and Shih-fu Chang Graph Transduction via Alternating Minimization Jun Wang, Tony Jebara, and Shih-fu Chang 1 Outline of the presentation Brief introduction and related work Problems with Graph Labeling Imbalanced labels

More information

Super-resolution on Text Image Sequences

Super-resolution on Text Image Sequences November 4, 2004 Outline Outline Geometric Distortion Optical/Motion Blurring Down-Sampling Total Variation Basic Idea Outline Geometric Distortion Optical/Motion Blurring Down-Sampling No optical/image

More information

Experimental Data and Training

Experimental Data and Training Modeling and Control of Dynamic Systems Experimental Data and Training Mihkel Pajusalu Alo Peets Tartu, 2008 1 Overview Experimental data Designing input signal Preparing data for modeling Training Criterion

More information

What is machine learning?

What is machine learning? Machine learning, pattern recognition and statistical data modelling Lecture 12. The last lecture Coryn Bailer-Jones 1 What is machine learning? Data description and interpretation finding simpler relationship

More information

DS Machine Learning and Data Mining I. Alina Oprea Associate Professor, CCIS Northeastern University

DS Machine Learning and Data Mining I. Alina Oprea Associate Professor, CCIS Northeastern University DS 4400 Machine Learning and Data Mining I Alina Oprea Associate Professor, CCIS Northeastern University January 24 2019 Logistics HW 1 is due on Friday 01/25 Project proposal: due Feb 21 1 page description

More information

Semi-supervised Data Representation via Affinity Graph Learning

Semi-supervised Data Representation via Affinity Graph Learning 1 Semi-supervised Data Representation via Affinity Graph Learning Weiya Ren 1 1 College of Information System and Management, National University of Defense Technology, Changsha, Hunan, P.R China, 410073

More information

Convex Optimization MLSS 2015

Convex Optimization MLSS 2015 Convex Optimization MLSS 2015 Constantine Caramanis The University of Texas at Austin The Optimization Problem minimize : f (x) subject to : x X. The Optimization Problem minimize : f (x) subject to :

More information

Convolution Neural Nets meet

Convolution Neural Nets meet Convolution Neural Nets meet PDE s Eldad Haber Lars Ruthotto SIAM CS&E 2017 Convolution Neural Networks (CNN) Meet PDE s Optimization Multiscale Example Future work CNN - A quick overview Neural Networks

More information

Semi-supervised Learning

Semi-supervised Learning Semi-supervised Learning Piyush Rai CS5350/6350: Machine Learning November 8, 2011 Semi-supervised Learning Supervised Learning models require labeled data Learning a reliable model usually requires plenty

More information

The K-modes and Laplacian K-modes algorithms for clustering

The K-modes and Laplacian K-modes algorithms for clustering The K-modes and Laplacian K-modes algorithms for clustering Miguel Á. Carreira-Perpiñán Electrical Engineering and Computer Science University of California, Merced http://faculty.ucmerced.edu/mcarreira-perpinan

More information

Optimization for Machine Learning

Optimization for Machine Learning with a focus on proximal gradient descent algorithm Department of Computer Science and Engineering Outline 1 History & Trends 2 Proximal Gradient Descent 3 Three Applications A Brief History A. Convex

More information

Optimization Plugin for RapidMiner. Venkatesh Umaashankar Sangkyun Lee. Technical Report 04/2012. technische universität dortmund

Optimization Plugin for RapidMiner. Venkatesh Umaashankar Sangkyun Lee. Technical Report 04/2012. technische universität dortmund Optimization Plugin for RapidMiner Technical Report Venkatesh Umaashankar Sangkyun Lee 04/2012 technische universität dortmund Part of the work on this technical report has been supported by Deutsche Forschungsgemeinschaft

More information

Deep Learning via Semi-Supervised Embedding. Jason Weston, Frederic Ratle and Ronan Collobert Presented by: Janani Kalyanam

Deep Learning via Semi-Supervised Embedding. Jason Weston, Frederic Ratle and Ronan Collobert Presented by: Janani Kalyanam Deep Learning via Semi-Supervised Embedding Jason Weston, Frederic Ratle and Ronan Collobert Presented by: Janani Kalyanam Review Deep Learning Extract low-level features first. Extract more complicated

More information

Conditional Random Fields and beyond D A N I E L K H A S H A B I C S U I U C,

Conditional Random Fields and beyond D A N I E L K H A S H A B I C S U I U C, Conditional Random Fields and beyond D A N I E L K H A S H A B I C S 5 4 6 U I U C, 2 0 1 3 Outline Modeling Inference Training Applications Outline Modeling Problem definition Discriminative vs. Generative

More information

The exam is closed book, closed notes except your one-page (two-sided) cheat sheet.

The 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 information

Programming, numerics and optimization

Programming, numerics and optimization Programming, numerics and optimization Lecture C-4: Constrained optimization Łukasz Jankowski ljank@ippt.pan.pl Institute of Fundamental Technological Research Room 4.32, Phone +22.8261281 ext. 428 June

More information

Graph-based Techniques for Searching Large-Scale Noisy Multimedia Data

Graph-based Techniques for Searching Large-Scale Noisy Multimedia Data Graph-based Techniques for Searching Large-Scale Noisy Multimedia Data Shih-Fu Chang Department of Electrical Engineering Department of Computer Science Columbia University Joint work with Jun Wang (IBM),

More information

Bilevel Sparse Coding

Bilevel Sparse Coding Adobe Research 345 Park Ave, San Jose, CA Mar 15, 2013 Outline 1 2 The learning model The learning algorithm 3 4 Sparse Modeling Many types of sensory data, e.g., images and audio, are in high-dimensional

More information

Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization. Author: Martin Jaggi Presenter: Zhongxing Peng

Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization. Author: Martin Jaggi Presenter: Zhongxing Peng Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization Author: Martin Jaggi Presenter: Zhongxing Peng Outline 1. Theoretical Results 2. Applications Outline 1. Theoretical Results 2. Applications

More information

SVM in Oracle Database 10g: Removing the Barriers to Widespread Adoption of Support Vector Machines

SVM in Oracle Database 10g: Removing the Barriers to Widespread Adoption of Support Vector Machines SVM in Oracle Database 10g: Removing the Barriers to Widespread Adoption of Support Vector Machines Boriana Milenova, Joseph Yarmus, Marcos Campos Data Mining Technologies Oracle Overview Support Vector

More information

ELEG Compressive Sensing and Sparse Signal Representations

ELEG Compressive Sensing and Sparse Signal Representations ELEG 867 - Compressive Sensing and Sparse Signal Representations Gonzalo R. Arce Depart. of Electrical and Computer Engineering University of Delaware Fall 211 Compressive Sensing G. Arce Fall, 211 1 /

More information

Computational Statistics The basics of maximum likelihood estimation, Bayesian estimation, object recognitions

Computational Statistics The basics of maximum likelihood estimation, Bayesian estimation, object recognitions Computational Statistics The basics of maximum likelihood estimation, Bayesian estimation, object recognitions Thomas Giraud Simon Chabot October 12, 2013 Contents 1 Discriminant analysis 3 1.1 Main idea................................

More information

Machine Learning / Jan 27, 2010

Machine Learning / Jan 27, 2010 Revisiting Logistic Regression & Naïve Bayes Aarti Singh Machine Learning 10-701/15-781 Jan 27, 2010 Generative and Discriminative Classifiers Training classifiers involves learning a mapping f: X -> Y,

More information

Learning Algorithms for Medical Image Analysis. Matteo Santoro slipguru

Learning Algorithms for Medical Image Analysis. Matteo Santoro slipguru Learning Algorithms for Medical Image Analysis Matteo Santoro slipguru santoro@disi.unige.it June 8, 2010 Outline 1. learning-based strategies for quantitative image analysis 2. automatic annotation of

More information

GRAPH BASED SEMI-SUPERVISED LEARNING IN COMPUTER VISION

GRAPH BASED SEMI-SUPERVISED LEARNING IN COMPUTER VISION GRAPH BASED SEMI-SUPERVISED LEARNING IN COMPUTER VISION by NING HUANG A dissertation submitted to the Graduate School New Brunswick Rutgers, The State University of New Jersey in conjunction with The Graduate

More information

Locally Linear Landmarks for large-scale manifold learning

Locally Linear Landmarks for large-scale manifold learning Locally Linear Landmarks for large-scale manifold learning Max Vladymyrov and Miguel Á. Carreira-Perpiñán Electrical Engineering and Computer Science University of California, Merced http://eecs.ucmerced.edu

More information

Theoretical Concepts of Machine Learning

Theoretical Concepts of Machine Learning Theoretical Concepts of Machine Learning Part 2 Institute of Bioinformatics Johannes Kepler University, Linz, Austria Outline 1 Introduction 2 Generalization Error 3 Maximum Likelihood 4 Noise Models 5

More information

A comparison of Algorithms for Sparse Matrix. Real-time Multibody Dynamic Simulation

A comparison of Algorithms for Sparse Matrix. Real-time Multibody Dynamic Simulation A comparison of Algorithms for Sparse Matrix Factoring and Variable Reordering aimed at Real-time Multibody Dynamic Simulation Jose-Luis Torres-Moreno, Jose-Luis Blanco, Javier López-Martínez, Antonio

More information

A Brief Look at Optimization

A Brief Look at Optimization A Brief Look at Optimization CSC 412/2506 Tutorial David Madras January 18, 2018 Slides adapted from last year s version Overview Introduction Classes of optimization problems Linear programming Steepest

More information

Machine Learning Classifiers and Boosting

Machine Learning Classifiers and Boosting Machine Learning Classifiers and Boosting Reading Ch 18.6-18.12, 20.1-20.3.2 Outline Different types of learning problems Different types of learning algorithms Supervised learning Decision trees Naïve

More information

Network Traffic Measurements and Analysis

Network Traffic Measurements and Analysis DEIB - Politecnico di Milano Fall, 2017 Sources Hastie, Tibshirani, Friedman: The Elements of Statistical Learning James, Witten, Hastie, Tibshirani: An Introduction to Statistical Learning Andrew Ng:

More information

Large Scale Manifold Transduction

Large Scale Manifold Transduction Large Scale Manifold Transduction Michael Karlen, Jason Weston, Ayse Erkan & Ronan Collobert NEC Labs America, Princeton, USA Ećole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland New York University,

More information

Convex and Distributed Optimization. Thomas Ropars

Convex and Distributed Optimization. Thomas Ropars >>> Presentation of this master2 course Convex and Distributed Optimization Franck Iutzeler Jérôme Malick Thomas Ropars Dmitry Grishchenko from LJK, the applied maths and computer science laboratory and

More information

Introduction to Optimization Problems and Methods

Introduction to Optimization Problems and Methods Introduction to Optimization Problems and Methods wjch@umich.edu December 10, 2009 Outline 1 Linear Optimization Problem Simplex Method 2 3 Cutting Plane Method 4 Discrete Dynamic Programming Problem Simplex

More information

A Taxonomy of Semi-Supervised Learning Algorithms

A Taxonomy of Semi-Supervised Learning Algorithms A Taxonomy of Semi-Supervised Learning Algorithms Olivier Chapelle Max Planck Institute for Biological Cybernetics December 2005 Outline 1 Introduction 2 Generative models 3 Low density separation 4 Graph

More information

The Alternating Direction Method of Multipliers

The Alternating Direction Method of Multipliers The Alternating Direction Method of Multipliers With Adaptive Step Size Selection Peter Sutor, Jr. Project Advisor: Professor Tom Goldstein October 8, 2015 1 / 30 Introduction Presentation Outline 1 Convex

More information

Lecture 12: Feasible direction methods

Lecture 12: Feasible direction methods Lecture 12 Lecture 12: Feasible direction methods Kin Cheong Sou December 2, 2013 TMA947 Lecture 12 Lecture 12: Feasible direction methods 1 / 1 Feasible-direction methods, I Intro Consider the problem

More information

Humanoid Robotics. Least Squares. Maren Bennewitz

Humanoid Robotics. Least Squares. Maren Bennewitz Humanoid Robotics Least Squares Maren Bennewitz Goal of This Lecture Introduction into least squares Use it yourself for odometry calibration, later in the lecture: camera and whole-body self-calibration

More information

Machine Learning: Think Big and Parallel

Machine Learning: Think Big and Parallel Day 1 Inderjit S. Dhillon Dept of Computer Science UT Austin CS395T: Topics in Multicore Programming Oct 1, 2013 Outline Scikit-learn: Machine Learning in Python Supervised Learning day1 Regression: Least

More information

A fast algorithm for sparse reconstruction based on shrinkage, subspace optimization and continuation [Wen,Yin,Goldfarb,Zhang 2009]

A fast algorithm for sparse reconstruction based on shrinkage, subspace optimization and continuation [Wen,Yin,Goldfarb,Zhang 2009] A fast algorithm for sparse reconstruction based on shrinkage, subspace optimization and continuation [Wen,Yin,Goldfarb,Zhang 2009] Yongjia Song University of Wisconsin-Madison April 22, 2010 Yongjia Song

More information

A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images

A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images Marc Aurelio Ranzato Yann LeCun Courant Institute of Mathematical Sciences New York University - New York, NY 10003 Abstract

More information

Kernel-based Transductive Learning with Nearest Neighbors

Kernel-based Transductive Learning with Nearest Neighbors Kernel-based Transductive Learning with Nearest Neighbors Liangcai Shu, Jinhui Wu, Lei Yu, and Weiyi Meng Dept. of Computer Science, SUNY at Binghamton Binghamton, New York 13902, U. S. A. {lshu,jwu6,lyu,meng}@cs.binghamton.edu

More information

Convex Optimization CMU-10725

Convex Optimization CMU-10725 Convex Optimization CMU-10725 Conjugate Direction Methods Barnabás Póczos & Ryan Tibshirani Conjugate Direction Methods 2 Books to Read David G. Luenberger, Yinyu Ye: Linear and Nonlinear Programming Nesterov:

More information

REGRESSION ANALYSIS : LINEAR BY MAUAJAMA FIRDAUS & TULIKA SAHA

REGRESSION ANALYSIS : LINEAR BY MAUAJAMA FIRDAUS & TULIKA SAHA REGRESSION ANALYSIS : LINEAR BY MAUAJAMA FIRDAUS & TULIKA SAHA MACHINE LEARNING It is the science of getting computer to learn without being explicitly programmed. Machine learning is an area of artificial

More information

Radial Basis Function Networks: Algorithms

Radial Basis Function Networks: Algorithms Radial Basis Function Networks: Algorithms Neural Computation : Lecture 14 John A. Bullinaria, 2015 1. The RBF Mapping 2. The RBF Network Architecture 3. Computational Power of RBF Networks 4. Training

More information

Application of Spectral Clustering Algorithm

Application of Spectral Clustering Algorithm 1/27 Application of Spectral Clustering Algorithm Danielle Middlebrooks dmiddle1@math.umd.edu Advisor: Kasso Okoudjou kasso@umd.edu Department of Mathematics University of Maryland- College Park Advance

More information

Class 6 Large-Scale Image Classification

Class 6 Large-Scale Image Classification Class 6 Large-Scale Image Classification Liangliang Cao, March 7, 2013 EECS 6890 Topics in Information Processing Spring 2013, Columbia University http://rogerioferis.com/visualrecognitionandsearch Visual

More information

CPSC 340: Machine Learning and Data Mining. Principal Component Analysis Fall 2016

CPSC 340: Machine Learning and Data Mining. Principal Component Analysis Fall 2016 CPSC 340: Machine Learning and Data Mining Principal Component Analysis Fall 2016 A2/Midterm: Admin Grades/solutions will be posted after class. Assignment 4: Posted, due November 14. Extra office hours:

More information

The Un-normalized Graph p-laplacian based Semi-supervised Learning Method and Speech Recognition Problem

The Un-normalized Graph p-laplacian based Semi-supervised Learning Method and Speech Recognition Problem Int. J. Advance Soft Compu. Appl, Vol. 9, No. 1, March 2017 ISSN 2074-8523 The Un-normalized Graph p-laplacian based Semi-supervised Learning Method and Speech Recognition Problem Loc Tran 1 and Linh Tran

More information

Overview Citation. ML Introduction. Overview Schedule. ML Intro Dataset. Introduction to Semi-Supervised Learning Review 10/4/2010

Overview Citation. ML Introduction. Overview Schedule. ML Intro Dataset. Introduction to Semi-Supervised Learning Review 10/4/2010 INFORMATICS SEMINAR SEPT. 27 & OCT. 4, 2010 Introduction to Semi-Supervised Learning Review 2 Overview Citation X. Zhu and A.B. Goldberg, Introduction to Semi- Supervised Learning, Morgan & Claypool Publishers,

More information

Variational Autoencoders. Sargur N. Srihari

Variational Autoencoders. Sargur N. Srihari Variational Autoencoders Sargur N. srihari@cedar.buffalo.edu Topics 1. Generative Model 2. Standard Autoencoder 3. Variational autoencoders (VAE) 2 Generative Model A variational autoencoder (VAE) is a

More information

The exam is closed book, closed notes except your one-page cheat sheet.

The exam is closed book, closed notes except your one-page cheat sheet. CS 189 Fall 2015 Introduction to Machine Learning Final Please do not turn over the page before you are instructed to do so. You have 2 hours and 50 minutes. Please write your initials on the top-right

More information

Full waveform inversion by deconvolution gradient method

Full waveform inversion by deconvolution gradient method Full waveform inversion by deconvolution gradient method Fuchun Gao*, Paul Williamson, Henri Houllevigue, Total), 2012 Lei Fu Rice University November 14, 2012 Outline Introduction Method Implementation

More information

Matching. Compare region of image to region of image. Today, simplest kind of matching. Intensities similar.

Matching. Compare region of image to region of image. Today, simplest kind of matching. Intensities similar. Matching Compare region of image to region of image. We talked about this for stereo. Important for motion. Epipolar constraint unknown. But motion small. Recognition Find object in image. Recognize object.

More information

PRIMAL-DUAL INTERIOR POINT METHOD FOR LINEAR PROGRAMMING. 1. Introduction

PRIMAL-DUAL INTERIOR POINT METHOD FOR LINEAR PROGRAMMING. 1. Introduction PRIMAL-DUAL INTERIOR POINT METHOD FOR LINEAR PROGRAMMING KELLER VANDEBOGERT AND CHARLES LANNING 1. Introduction Interior point methods are, put simply, a technique of optimization where, given a problem

More information

1 Training/Validation/Testing

1 Training/Validation/Testing CPSC 340 Final (Fall 2015) Name: Student Number: Please enter your information above, turn off cellphones, space yourselves out throughout the room, and wait until the official start of the exam to begin.

More information

CS 179 Lecture 16. Logistic Regression & Parallel SGD

CS 179 Lecture 16. Logistic Regression & Parallel SGD CS 179 Lecture 16 Logistic Regression & Parallel SGD 1 Outline logistic regression (stochastic) gradient descent parallelizing SGD for neural nets (with emphasis on Google s distributed neural net implementation)

More information

A Course in Machine Learning

A Course in Machine Learning A Course in Machine Learning Hal Daumé III 13 UNSUPERVISED LEARNING If you have access to labeled training data, you know what to do. This is the supervised setting, in which you have a teacher telling

More information

Recent Developments in Model-based Derivative-free Optimization

Recent Developments in Model-based Derivative-free Optimization Recent Developments in Model-based Derivative-free Optimization Seppo Pulkkinen April 23, 2010 Introduction Problem definition The problem we are considering is a nonlinear optimization problem with constraints:

More information

1. Introduction. performance of numerical methods. complexity bounds. structural convex optimization. course goals and topics

1. Introduction. performance of numerical methods. complexity bounds. structural convex optimization. course goals and topics 1. Introduction EE 546, Univ of Washington, Spring 2016 performance of numerical methods complexity bounds structural convex optimization course goals and topics 1 1 Some course info Welcome to EE 546!

More information

Detection of Man-made Structures in Natural Images

Detection of Man-made Structures in Natural Images Detection of Man-made Structures in Natural Images Tim Rees December 17, 2004 Abstract Object detection in images is a very active research topic in many disciplines. Probabilistic methods have been applied

More information

Modern Methods of Data Analysis - WS 07/08

Modern Methods of Data Analysis - WS 07/08 Modern Methods of Data Analysis Lecture XV (04.02.08) Contents: Function Minimization (see E. Lohrmann & V. Blobel) Optimization Problem Set of n independent variables Sometimes in addition some constraints

More information

Neural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani

Neural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani Neural Networks CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Biological and artificial neural networks Feed-forward neural networks Single layer

More information

A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images

A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images Marc Aurelio Ranzato Yann LeCun Courant Institute of Mathematical Sciences New York University - New York, NY 10003 Abstract

More information

MULTICORE LEARNING ALGORITHM

MULTICORE LEARNING ALGORITHM MULTICORE LEARNING ALGORITHM CHENG-TAO CHU, YI-AN LIN, YUANYUAN YU 1. Summary The focus of our term project is to apply the map-reduce principle to a variety of machine learning algorithms that are computationally

More information

Unsupervised Outlier Detection and Semi-Supervised Learning

Unsupervised Outlier Detection and Semi-Supervised Learning Unsupervised Outlier Detection and Semi-Supervised Learning Adam Vinueza Department of Computer Science University of Colorado Boulder, Colorado 832 vinueza@colorado.edu Gregory Z. Grudic Department of

More information

Parallel and Distributed Sparse Optimization Algorithms

Parallel and Distributed Sparse Optimization Algorithms Parallel and Distributed Sparse Optimization Algorithms Part I Ruoyu Li 1 1 Department of Computer Science and Engineering University of Texas at Arlington March 19, 2015 Ruoyu Li (UTA) Parallel and Distributed

More information

SemiBoost: Boosting for Semi-supervised Learning

SemiBoost: Boosting for Semi-supervised Learning To appear in the IEEE Transactions on Pattern Analysis and Machine Intelligence. SemiBoost: Boosting for Semi-supervised Learning Pavan Kumar Mallapragada, Student Member, IEEE, Rong Jin, Member, IEEE,

More information

Data fusion and multi-cue data matching using diffusion maps

Data fusion and multi-cue data matching using diffusion maps Data fusion and multi-cue data matching using diffusion maps Stéphane Lafon Collaborators: Raphy Coifman, Andreas Glaser, Yosi Keller, Steven Zucker (Yale University) Part of this work was supported by

More information

Asynchronous Multi-Task Learning

Asynchronous Multi-Task Learning Asynchronous Multi-Task Learning Inci M. Baytas, Ming Yan, Anil K. Jain and Jiayu Zhou December 14th, 2016 ICDM 2016 Inci M. Baytas, Ming Yan, Anil K. Jain and Jiayu Zhou 1 Outline 1 Introduction 2 Solving

More information

Unsupervised and Semi-Supervised Learning vial 1 -Norm Graph

Unsupervised and Semi-Supervised Learning vial 1 -Norm Graph Unsupervised and Semi-Supervised Learning vial -Norm Graph Feiping Nie, Hua Wang, Heng Huang, Chris Ding Department of Computer Science and Engineering University of Texas, Arlington, TX 769, USA {feipingnie,huawangcs}@gmail.com,

More information

Training of Neural Networks. Q.J. Zhang, Carleton University

Training of Neural Networks. Q.J. Zhang, Carleton University Training of Neural Networks Notation: x: input of the original modeling problem or the neural network y: output of the original modeling problem or the neural network w: internal weights/parameters of

More information

Graph-based Semi- Supervised Learning as Optimization

Graph-based Semi- Supervised Learning as Optimization Graph-based Semi- Supervised Learning as Optimization Partha Pratim Talukdar CMU Machine Learning with Large Datasets (10-605) April 3, 2012 Graph-based Semi-Supervised Learning 0.2 0.1 0.2 0.3 0.3 0.2

More information

Unlabeled Data Classification by Support Vector Machines

Unlabeled Data Classification by Support Vector Machines Unlabeled Data Classification by Support Vector Machines Glenn Fung & Olvi L. Mangasarian University of Wisconsin Madison www.cs.wisc.edu/ olvi www.cs.wisc.edu/ gfung The General Problem Given: Points

More information

CS 340 Lec. 4: K-Nearest Neighbors

CS 340 Lec. 4: K-Nearest Neighbors CS 340 Lec. 4: K-Nearest Neighbors AD January 2011 AD () CS 340 Lec. 4: K-Nearest Neighbors January 2011 1 / 23 K-Nearest Neighbors Introduction Choice of Metric Overfitting and Underfitting Selection

More information

Locality Preserving Projections (LPP) Abstract

Locality Preserving Projections (LPP) Abstract Locality Preserving Projections (LPP) Xiaofei He Partha Niyogi Computer Science Department Computer Science Department The University of Chicago The University of Chicago Chicago, IL 60615 Chicago, IL

More information

Kernels and representation

Kernels and representation Kernels and representation Corso di AA, anno 2017/18, Padova Fabio Aiolli 20 Dicembre 2017 Fabio Aiolli Kernels and representation 20 Dicembre 2017 1 / 19 (Hierarchical) Representation Learning Hierarchical

More information

Visual Understanding via Multi-Feature Shared Learning with Global Consistency

Visual Understanding via Multi-Feature Shared Learning with Global Consistency Visual Understanding via Multi-Feature Shared Learning with Global Consistency Lei Zhang, Member, IEEE, and David Zhang, Fellow, IEEE Abstract Image/video data is usually represented with multiple visual

More information

Neural Networks: Optimization Part 1. Intro to Deep Learning, Fall 2018

Neural Networks: Optimization Part 1. Intro to Deep Learning, Fall 2018 Neural Networks: Optimization Part 1 Intro to Deep Learning, Fall 2018 1 Story so far Neural networks are universal approximators Can model any odd thing Provided they have the right architecture We must

More information

CS281 Section 3: Practical Optimization

CS281 Section 3: Practical Optimization CS281 Section 3: Practical Optimization David Duvenaud and Dougal Maclaurin Most parameter estimation problems in machine learning cannot be solved in closed form, so we often have to resort to numerical

More information