Learning From Data Lecture 5 Training Versus Testing
|
|
- Lindsay Cross
- 5 years ago
- Views:
Transcription
1 Learning From Data Lecture 5 Training Versus Testing The Two Questions of Learning Theory of Generalization (E in E out ) An Effective Number of Hypotheses A Combinatorial Puzzle M. Magdon-Ismail CSCI 4100/6100
2 recap: The Two Questions of Learning 1.Can we make sure that E out (g) is close enough to E in (g)? 2.Can we make E in (g) small enough? The Hoeffding generalization bound: out-of-sample error 1 E out (g) E in (g)+ 2N ln2 H δ }{{} generalization error bar Error H model complexity in-sample error H E in : training (eg. the practice exam) E out : testing (eg. the real exam) There is a tradeoff when picking H. c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 2 /18 Goal of generalization theory
3 What Will The Theory of Generalization Achieve? out-of-sample error E out (g) E in (g)+ 1 2N ln2 H δ Error model complexity in-sample error H H out-of-sample error E out (g) E in (g)+ 8 N ln4m H δ Error model complexity in-sample error model complexity The new bound will be applicable to infinite H. c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 3 /18 H is overkill
4 Why is H an Overkill How did H come in? Bad events B g = { E out (g) E in (g) > ǫ} B m = { E out (h m ) E in (h m ) > ǫ} B 1 B 2 We do not know which g, so use a worst case union bound. P[B g ] P[any B m ] H m=1 P[B m ]. B 3 B m are events (sets of outcomes); they can overlap. If the B m overlap, the union bound is loose. If many h m are similar, the B m overlap. There are effectively fewer than H hypotheses,. We can replace H by something smaller. H fails to account for similarity between hypotheses. c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 4 /18 Measuring diversity on N points
5 Measuring the Diversity (Size) of H We need a way to measure the diversity of H. A simple idea: Fix any set of N data points. If H is diverse it should be able to implement all functions...on these N points. c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 5 /18 Example: large H
6 A Data Set Reveals the True Colors of an H H c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 6 /18...through the eyes of D
7 A Data Set Reveals the True Colors of an H H H through the eyes of the D c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 7 /18 Just one dichotomy
8 A Data Set Reveals the True Colors of an H From the point of view of D, the entire H is just one dichotomy. c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 8 /18 An effective number of hypotheses
9 An Effective Number of Hypotheses If H is diverse it should be able to implement many dichotomys. H only captures the maximum possible diversity of H. Consider an h H, and a data set x 1,...,x N. h gives us an N-tuple of ±1 s: (h(x 1 ),...,h(x N )). A dichotomy of the inputs. If H is diverse, we get many different dichotomies. If H contains similar functions, we only get a few dichotomies. dichotomy The growth function quantifies this. c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 9 /18 Growth function
10 The Growth Function m H (N) Define the the restriction of H to the inputs x 1,x 2,...,x N : H(x 1,...,x N ) = {(h(x 1 ),...,h(x N )) h H} (set of dichotomies induced by H) The Growth Function m H (N) The largest set of dichotomies induced by H: m H (N) = max x 1,...,x N H(x 1,...,x N ). m H (N) 2 N. Can we replace H by m H, an effective number of hypotheses? Replacing H with 2 N is no help in the bound. (why?) We want m H (N) poly(n) to get a useful error bar. ( the error bar is ) 1 2 H ln 2N δ c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 10 /18 Example: 2-d perceptron
11 Example: 2-D Perceptron Model Cannot implement Can implement all 8 Can implement at most 14 m H (3) = 8 = 2 3. What is m H (5)? m H (4) = 14 < 2 4. c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 11 /18 Example: 1-d positive ray
12 Example: 1-D Positive Ray Model w 0 + x 1 x 2 x N h(x) = sign(x w 0 ) Consider N points. There are N +1 dichotomies depending on where you put w 0. m H (N) = N +1. c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 12 /18 Example: 2-d positive rectangle
13 Example: Positive Rectangles in 2-D N = 4 N = 5 x 2 x 2 x 1 x 3 x 1 x 3 x 4 x 4 x 4 H implements all dichotomies some point will be inside a rectangle defined by others m H (4) = 2 4 m H (5) < 2 5 We have not computed m H (5) not impossible, but tricky. c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 13 /18 The growth functions summarized
14 Example Growth Functions N D perceptron D pos. ray D pos. rectangles < 2 5 m H (N) drops below 2 N there is hope for the generalization bound. A break point is any n for which m H (n) < 2 n. c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 14 /18 Combinatorial puzzle: dichotomys on 3 points
15 A Combinatorial Puzzle x 1 x 2 x 3 A set of dichotomys c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 15 /18 Two points shattered
16 A Combinatorial Puzzle x 1 x 2 x 3 Two points are shattered c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 16 /18 Another set of dichotomys
17 A Combinatorial Puzzle x 1 x 2 x 3 No pair of points is shattered c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 17 /18 What about N = 4?
18 A Combinatorial Puzzle x 1 x 2 x 3 x 1 x 2 x 3 x 4. 4 dichotomies is max. If N = 4 how many possible dichotomys with no 2 points shattered? c AM L Creator: Malik Magdon-Ismail Training Versus Testing: 18 /18
Learning From Data Lecture 7 Approximation Versus Generalization
Learning From Data Lecture 7 Approimation Versus Generalization The VC Dimension Approimation Versus Generalization Bias and Variance The Learning Curve M. Magdon-Ismail CSCI 4100/6100 recap: The Vapnik-Chervonenkis
More informationECS171: Machine Learning
ECS171: Machine Learning Lecture 6: Training versus Testing (LFD 2.1) Cho-Jui Hsieh UC Davis Jan 29, 2018 Preamble to the theory Training versus testing Out-of-sample error (generalization error): What
More informationLearning From Data Lecture 3 Is Learning Feasible?
Learning From Data Lecture 3 Is Learning Feasible? Outside the Data Probability to the Rescue Learning vs. Verification Selection Bias - A Cartoon M. Magdon-Ismail CSCI 4100/6100 recap: The Perceptron
More informationLearning From Data Lecture 2 The Perceptron
Learning From Data Lecture 2 The Perceptron The Learning Setup A Simple Learning Algorithm: PLA Other Views of Learning Is Learning Feasible: A Puzzle M. Magdon-Ismail CSCI 4100/6100 recap: The Plan 1.
More informationLearning From Data Lecture 10 Nonlinear Transforms
Learning From Data Lecture 0 Nonlinear Transforms The Z-space Polynomial transforms Be careful M. Magdon-Ismail CSCI 400/600 recap: The Linear Model linear in w: makes the algorithms work linear in x:
More informationLearning From Data Lecture 13 Validation and Model Selection
Learning From Data Lecture 13 Validation and Model Selection The Validation Set Model Selection Cross Validation M. Magdon-Ismail CSCI 4100/6100 recap: Regularization Regularization combats the effects
More informationCSE 417T: Introduction to Machine Learning. Lecture 11: Review. Henry Chai 10/02/18
CSE 417T: Introduction to Machine Learning Lecture 11: Review Henry Chai 10/02/18 Unknown Target Function!: # % Training data Formal Setup & = ( ), + ),, ( -, + - Learning Algorithm 2 Hypothesis Set H
More informationORIE 4741: Learning with Big Messy Data. Generalization
ORIE 4741: Learning with Big Messy Data Generalization Professor Udell Operations Research and Information Engineering Cornell September 23, 2017 1 / 21 Announcements midterm 10/5 makeup exam 10/2, by
More informationLearning From Data Lecture 8 Linear Classification and Regression
Learning From Data Lecture 8 Linear Classification and Regression Linear Classification Linear Regression M. Magdon-Ismail CSCI 4100/6100 recap: Approximation Versus Generalization VC Analysis E out E
More informationLearning From Data Lecture 14 Three Learning Principles
Learning From Data Lecture 14 Three Learning Principles Occam s Razor Sampling Bias Data Snooping M. Magdon-Ismail CSCI 4100/6100 recap: Validation and Cross Validation Validation Cross Validation D (N)
More informationCS340 Machine learning Lecture 5 Learning theory cont'd. Some slides are borrowed from Stuart Russell and Thorsten Joachims
CS340 Machine learning Lecture 5 Learning theory cont'd Some slides are borrowed from Stuart Russell and Thorsten Joachims Inductive learning Simplest form: learn a function from examples f is the target
More informationCS340 Machine learning Lecture 4 Learning theory. Some slides are borrowed from Sebastian Thrun and Stuart Russell
CS340 Machine learning Lecture 4 Learning theory Some slides are borrowed from Sebastian Thrun and Stuart Russell Announcement What: Workshop on applying for NSERC scholarships and for entry to graduate
More informationComputational Learning Theory. CS534 - Machine Learning
Computational Learning Theory CS534 Machine Learning Introduction Computational learning theory Provides a theoretical analysis of learning Shows when a learning algorithm can be expected to succeed Shows
More informationMachine Learning Foundations
Machine Learning Foundations ( 機器學習基石 ) Lecture 4: Feasibility of Learning Hsuan-Tien Lin ( 林軒田 ) htlin@csie.ntu.edu.tw Department of Computer Science & Information Engineering National Taiwan University
More informationVC Dimension Review. The purpose of this document is to review VC dimension and PAC learning for infinite hypothesis spaces.
VC Dimension Review The purpose of this document is to review VC dimension and PAC learning for infinite hypothesis spaces. Previously, in discussing PAC learning, we were trying to answer questions about
More informationLearning From Data Lecture 9 Logistic Regression and Gradient Descent
Learning From Data Lecture 9 Logistic Regression and Gradient Descent Logistic Regression Gradient Descent M. Magdon-Ismail CSCI 4100/6100 recap: Linear Classification and Regression The linear signal:
More informationLearning From Data Lecture 15 Reflecting on Our Path - Epilogue to Part I
Learning From Data Lecture 15 Reflecting on Our Path - Epilogue to Part I What We Did The Machine Learning Zoo Moving Forward M Magdon-Ismail CSCI 4100/6100 recap: Three Learning Principles Scientist 2
More informationIntroduction to Machine Learning
Introduction to Machine Learning PAC Learning and VC Dimension Varun Chandola Computer Science & Engineering State University of New York at Buffalo Buffalo, NY, USA chandola@buffalo.edu Chandola@UB CSE
More informationLearning From Data Lecture 26 Kernel Machines
Learning From Data Lecture 26 Kernel Machines Popular Kernels The Kernel Measures Similarity Kernels in Different Applications M Magdon-Ismail CSCI 4100/6100 recap: The Kernel Allows Us to Bypass Z-space
More informationLearning From Data Lecture 25 The Kernel Trick
Learning From Data Lecture 25 The Kernel Trick Learning with only inner products The Kernel M. Magdon-Ismail CSCI 400/600 recap: Large Margin is Better Controling Overfitting Non-Separable Data 0.08 random
More informationComputational Learning Theory. Definitions
Computational Learning Theory Computational learning theory is interested in theoretical analyses of the following issues. What is needed to learn effectively? Sample complexity. How many examples? Computational
More informationActive Learning and Optimized Information Gathering
Active Learning and Optimized Information Gathering Lecture 7 Learning Theory CS 101.2 Andreas Krause Announcements Project proposal: Due tomorrow 1/27 Homework 1: Due Thursday 1/29 Any time is ok. Office
More informationFoundations of Computer Science Lecture 14 Advanced Counting
Foundations of Computer Science Lecture 14 Advanced Counting Sequences with Repetition Union of Overlapping Sets: Inclusion-Exclusion Pigeonhole Principle Last Time To count complex objects, construct
More informationStatistical and Computational Learning Theory
Statistical and Computational Learning Theory Fundamental Question: Predict Error Rates Given: Find: The space H of hypotheses The number and distribution of the training examples S The complexity of the
More informationTHE VAPNIK- CHERVONENKIS DIMENSION and LEARNABILITY
THE VAPNIK- CHERVONENKIS DIMENSION and LEARNABILITY Dan A. Simovici UMB, Doctoral Summer School Iasi, Romania What is Machine Learning? The Vapnik-Chervonenkis Dimension Probabilistic Learning Potential
More informationLearning From Data Lecture 12 Regularization
Learning From Data Lecture 12 Regularization Constraining the Model Weight Decay Augmented Error M. Magdon-Ismail CSCI 4100/6100 recap: Overfitting Fitting the data more than is warranted Data Target Fit
More informationCOMP9444: Neural Networks. Vapnik Chervonenkis Dimension, PAC Learning and Structural Risk Minimization
: Neural Networks Vapnik Chervonenkis Dimension, PAC Learning and Structural Risk Minimization 11s2 VC-dimension and PAC-learning 1 How good a classifier does a learner produce? Training error is the precentage
More informationComputational Learning Theory
CS 446 Machine Learning Fall 2016 OCT 11, 2016 Computational Learning Theory Professor: Dan Roth Scribe: Ben Zhou, C. Cervantes 1 PAC Learning We want to develop a theory to relate the probability of successful
More informationIntroduction to Statistical Learning Theory
Introduction to Statistical Learning Theory Definition Reminder: We are given m samples {(x i, y i )} m i=1 Dm and a hypothesis space H and we wish to return h H minimizing L D (h) = E[l(h(x), y)]. Problem
More informationHomework # 3. Due Monday, October 22, 2018, at 2:00 PM PDT
CS/CNS/EE 156a Learning Systems Caltech - Fall 018 http://cs156.caltech.edu (Learning From Data campus version Homework # 3 Due Monday, October, 018, at :00 PM PDT Definitions and notation follow the lectures.
More informationCOS 511: Theoretical Machine Learning. Lecturer: Rob Schapire Lecture #5 Scribe: Allen(Zhelun) Wu February 19, ). Then: Pr[err D (h A ) > ɛ] δ
COS 511: Theoretical Machine Learning Lecturer: Rob Schapire Lecture #5 Scribe: Allen(Zhelun) Wu February 19, 018 Review Theorem (Occam s Razor). Say algorithm A finds a hypothesis h A H consistent with
More informationUnderstanding Generalization Error: Bounds and Decompositions
CIS 520: Machine Learning Spring 2018: Lecture 11 Understanding Generalization Error: Bounds and Decompositions Lecturer: Shivani Agarwal Disclaimer: These notes are designed to be a supplement to the
More informationLecture Learning infinite hypothesis class via VC-dimension and Rademacher complexity;
CSCI699: Topics in Learning and Game Theory Lecture 2 Lecturer: Ilias Diakonikolas Scribes: Li Han Today we will cover the following 2 topics: 1. Learning infinite hypothesis class via VC-dimension and
More informationComputational Learning Theory
Computational Learning Theory Slides by and Nathalie Japkowicz (Reading: R&N AIMA 3 rd ed., Chapter 18.5) Computational Learning Theory Inductive learning: given the training set, a learning algorithm
More informationComputational Learning Theory (VC Dimension)
Computational Learning Theory (VC Dimension) 1 Difficulty of machine learning problems 2 Capabilities of machine learning algorithms 1 Version Space with associated errors error is the true error, r is
More informationCS 6375: Machine Learning Computational Learning Theory
CS 6375: Machine Learning Computational Learning Theory Vibhav Gogate The University of Texas at Dallas Many slides borrowed from Ray Mooney 1 Learning Theory Theoretical characterizations of Difficulty
More informationGeneralization Bounds in Machine Learning. Presented by: Afshin Rostamizadeh
Generalization Bounds in Machine Learning Presented by: Afshin Rostamizadeh Outline Introduction to generalization bounds. Examples: VC-bounds Covering Number bounds Rademacher bounds Stability bounds
More informationLearning Theory. Aar$ Singh and Barnabas Poczos. Machine Learning / Apr 17, Slides courtesy: Carlos Guestrin
Learning Theory Aar$ Singh and Barnabas Poczos Machine Learning 10-701/15-781 Apr 17, 2014 Slides courtesy: Carlos Guestrin Learning Theory We have explored many ways of learning from data But How good
More informationComputational Learning Theory
1 Computational Learning Theory 2 Computational learning theory Introduction Is it possible to identify classes of learning problems that are inherently easy or difficult? Can we characterize the number
More informationMachine Learning. Model Selection and Validation. Fabio Vandin November 7, 2017
Machine Learning Model Selection and Validation Fabio Vandin November 7, 2017 1 Model Selection When we have to solve a machine learning task: there are different algorithms/classes algorithms have parameters
More informationHypothesis Testing and Computational Learning Theory. EECS 349 Machine Learning With slides from Bryan Pardo, Tom Mitchell
Hypothesis Testing and Computational Learning Theory EECS 349 Machine Learning With slides from Bryan Pardo, Tom Mitchell Overview Hypothesis Testing: How do we know our learners are good? What does performance
More informationLearning Theory. Piyush Rai. CS5350/6350: Machine Learning. September 27, (CS5350/6350) Learning Theory September 27, / 14
Learning Theory Piyush Rai CS5350/6350: Machine Learning September 27, 2011 (CS5350/6350) Learning Theory September 27, 2011 1 / 14 Why Learning Theory? We want to have theoretical guarantees about our
More informationComputational Learning Theory
Computational Learning Theory Sinh Hoa Nguyen, Hung Son Nguyen Polish-Japanese Institute of Information Technology Institute of Mathematics, Warsaw University February 14, 2006 inh Hoa Nguyen, Hung Son
More informationLearning Theory. Sridhar Mahadevan. University of Massachusetts. p. 1/38
Learning Theory Sridhar Mahadevan mahadeva@cs.umass.edu University of Massachusetts p. 1/38 Topics Probability theory meet machine learning Concentration inequalities: Chebyshev, Chernoff, Hoeffding, and
More information1 A Lower Bound on Sample Complexity
COS 511: Theoretical Machine Learning Lecturer: Rob Schapire Lecture #7 Scribe: Chee Wei Tan February 25, 2008 1 A Lower Bound on Sample Complexity In the last lecture, we stopped at the lower bound on
More informationClassification: The PAC Learning Framework
Classification: The PAC Learning Framework Machine Learning: Jordan Boyd-Graber University of Colorado Boulder LECTURE 5 Slides adapted from Eli Upfal Machine Learning: Jordan Boyd-Graber Boulder Classification:
More informationVC dimension and Model Selection
VC dimension and Model Selection Overview PAC model: review VC dimension: Definition Examples Sample: Lower bound Upper bound!!! Model Selection Introduction to Machine Learning 2 PAC model: Setting A
More informationLearning Theory. Machine Learning CSE546 Carlos Guestrin University of Washington. November 25, Carlos Guestrin
Learning Theory Machine Learning CSE546 Carlos Guestrin University of Washington November 25, 2013 Carlos Guestrin 2005-2013 1 What now n We have explored many ways of learning from data n But How good
More informationCS 498F: Machine Learning Fall 2010
Instructions: Make sure you write your name on every page you submit. This is a closed-book, closed-note exam. There are 8 questions + 1 extra credit question. Some reminders of material you may need is
More informationWeb-Mining Agents Computational Learning Theory
Web-Mining Agents Computational Learning Theory Prof. Dr. Ralf Möller Dr. Özgür Özcep Universität zu Lübeck Institut für Informationssysteme Tanya Braun (Exercise Lab) Computational Learning Theory (Adapted)
More informationDan Roth 461C, 3401 Walnut
CIS 519/419 Applied Machine Learning www.seas.upenn.edu/~cis519 Dan Roth danroth@seas.upenn.edu http://www.cis.upenn.edu/~danroth/ 461C, 3401 Walnut Slides were created by Dan Roth (for CIS519/419 at Penn
More information1 Proof of learning bounds
COS 511: Theoretical Machine Learning Lecturer: Rob Schapire Lecture #4 Scribe: Akshay Mittal February 13, 2013 1 Proof of learning bounds For intuition of the following theore, suppose there exists a
More informationDoes Unlabeled Data Help?
Does Unlabeled Data Help? Worst-case Analysis of the Sample Complexity of Semi-supervised Learning. Ben-David, Lu and Pal; COLT, 2008. Presentation by Ashish Rastogi Courant Machine Learning Seminar. Outline
More informationPAC-learning, VC Dimension and Margin-based Bounds
More details: General: http://www.learning-with-kernels.org/ Example of more complex bounds: http://www.research.ibm.com/people/t/tzhang/papers/jmlr02_cover.ps.gz PAC-learning, VC Dimension and Margin-based
More informationMachine Learning. Computational Learning Theory. Le Song. CSE6740/CS7641/ISYE6740, Fall 2012
Machine Learning CSE6740/CS7641/ISYE6740, Fall 2012 Computational Learning Theory Le Song Lecture 11, September 20, 2012 Based on Slides from Eric Xing, CMU Reading: Chap. 7 T.M book 1 Complexity of Learning
More information1 The Probably Approximately Correct (PAC) Model
COS 511: Theoretical Machine Learning Lecturer: Rob Schapire Lecture #3 Scribe: Yuhui Luo February 11, 2008 1 The Probably Approximately Correct (PAC) Model A target concept class C is PAC-learnable by
More informationMachine Learning. VC Dimension and Model Complexity. Eric Xing , Fall 2015
Machine Learning 10-701, Fall 2015 VC Dimension and Model Complexity Eric Xing Lecture 16, November 3, 2015 Reading: Chap. 7 T.M book, and outline material Eric Xing @ CMU, 2006-2015 1 Last time: PAC and
More informationMachine Learning. Lecture 9: Learning Theory. Feng Li.
Machine Learning Lecture 9: Learning Theory Feng Li fli@sdu.edu.cn https://funglee.github.io School of Computer Science and Technology Shandong University Fall 2018 Why Learning Theory How can we tell
More informationAn Introduction to No Free Lunch Theorems
February 2, 2012 Table of Contents Induction Learning without direct observation. Generalising from data. Modelling physical phenomena. The Problem of Induction David Hume (1748) How do we know an induced
More information10.1 The Formal Model
67577 Intro. to Machine Learning Fall semester, 2008/9 Lecture 10: The Formal (PAC) Learning Model Lecturer: Amnon Shashua Scribe: Amnon Shashua 1 We have see so far algorithms that explicitly estimate
More informationFoundations of Computer Science Lecture 23 Languages: What is Computation?
Foundations of Computer Science Lecture 23 Languages: What is Computation? A Formal Model of a Computing Problem Decision Problems and Languages Describing a Language: Regular Expressions Complexity of
More informationThe Vapnik-Chervonenkis Dimension
The Vapnik-Chervonenkis Dimension Prof. Dan A. Simovici UMB 1 / 91 Outline 1 Growth Functions 2 Basic Definitions for Vapnik-Chervonenkis Dimension 3 The Sauer-Shelah Theorem 4 The Link between VCD and
More informationCSC321 Lecture 4 The Perceptron Algorithm
CSC321 Lecture 4 The Perceptron Algorithm Roger Grosse and Nitish Srivastava January 17, 2017 Roger Grosse and Nitish Srivastava CSC321 Lecture 4 The Perceptron Algorithm January 17, 2017 1 / 1 Recap:
More informationComputational and Statistical Learning theory
Computational and Statistical Learning theory Problem set 2 Due: January 31st Email solutions to : karthik at ttic dot edu Notation : Input space : X Label space : Y = {±1} Sample : (x 1, y 1,..., (x n,
More informationSample complexity bounds for differentially private learning
Sample complexity bounds for differentially private learning Kamalika Chaudhuri University of California, San Diego Daniel Hsu Microsoft Research Outline 1. Learning and privacy model 2. Our results: sample
More informationLinear Regression. Machine Learning CSE546 Kevin Jamieson University of Washington. Oct 5, Kevin Jamieson 1
Linear Regression Machine Learning CSE546 Kevin Jamieson University of Washington Oct 5, 2017 1 The regression problem Given past sales data on zillow.com, predict: y = House sale price from x = {# sq.
More informationComputational Learning Theory. CS 486/686: Introduction to Artificial Intelligence Fall 2013
Computational Learning Theory CS 486/686: Introduction to Artificial Intelligence Fall 2013 1 Overview Introduction to Computational Learning Theory PAC Learning Theory Thanks to T Mitchell 2 Introduction
More informationComputational Learning Theory
09s1: COMP9417 Machine Learning and Data Mining Computational Learning Theory May 20, 2009 Acknowledgement: Material derived from slides for the book Machine Learning, Tom M. Mitchell, McGraw-Hill, 1997
More informationoutline Nonlinear transformation Error measures Noisy targets Preambles to the theory
Error and Noise outline Nonlinear transformation Error measures Noisy targets Preambles to the theory Linear is limited Data Hypothesis Linear in what? Linear regression implements Linear classification
More informationCS261: A Second Course in Algorithms Lecture #18: Five Essential Tools for the Analysis of Randomized Algorithms
CS261: A Second Course in Algorithms Lecture #18: Five Essential Tools for the Analysis of Randomized Algorithms Tim Roughgarden March 3, 2016 1 Preamble In CS109 and CS161, you learned some tricks of
More informationLinear models and the perceptron algorithm
8/5/6 Preliminaries Linear models and the perceptron algorithm Chapters, 3 Definition: The Euclidean dot product beteen to vectors is the expression dx T x = i x i The dot product is also referred to as
More informationLearning theory Lecture 4
Learning theory Lecture 4 David Sontag New York University Slides adapted from Carlos Guestrin & Luke Zettlemoyer What s next We gave several machine learning algorithms: Perceptron Linear support vector
More informationComputational Learning Theory
Computational Learning Theory Pardis Noorzad Department of Computer Engineering and IT Amirkabir University of Technology Ordibehesht 1390 Introduction For the analysis of data structures and algorithms
More informationPreliminaries. Definition: The Euclidean dot product between two vectors is the expression. i=1
90 8 80 7 70 6 60 0 8/7/ Preliminaries Preliminaries Linear models and the perceptron algorithm Chapters, T x + b < 0 T x + b > 0 Definition: The Euclidean dot product beteen to vectors is the expression
More informationIntro to Contemporary Math
Intro to Contemporary Math Unions and Intersections of Intervals Department of Mathematics UK Announcement You have a homework assignment due next Monday. Mini-exam 2 is next Wednesday. Unions and Intersections
More informationChapter 2 Linear Equations and Inequalities in One Variable
Chapter 2 Linear Equations and Inequalities in One Variable Section 2.1: Linear Equations in One Variable Section 2.3: Solving Formulas Section 2.5: Linear Inequalities in One Variable Section 2.6: Compound
More informationPreliminary check: are the terms that we are adding up go to zero or not? If not, proceed! If the terms a n are going to zero, pick another test.
Throughout these templates, let series. be a series. We hope to determine the convergence of this Divergence Test: If lim is not zero or does not exist, then the series diverges. Preliminary check: are
More informationComputational Learning Theory: Probably Approximately Correct (PAC) Learning. Machine Learning. Spring The slides are mainly from Vivek Srikumar
Computational Learning Theory: Probably Approximately Correct (PAC) Learning Machine Learning Spring 2018 The slides are mainly from Vivek Srikumar 1 This lecture: Computational Learning Theory The Theory
More informationClass 19. Daniel B. Rowe, Ph.D. Department of Mathematics, Statistics, and Computer Science. Marquette University MATH 1700
Class 19 Daniel B. Rowe, Ph.D. Department of Mathematics, Statistics, and Computer Science Copyright 2017 by D.B. Rowe 1 Agenda: Recap Chapter 8.3-8.4 Lecture Chapter 8.5 Go over Exam. Problem Solving
More informationIntroduction to Machine Learning
Introduction to Machine Learning Slides adapted from Eli Upfal Machine Learning: Jordan Boyd-Graber University of Maryland FEATURE ENGINEERING Machine Learning: Jordan Boyd-Graber UMD Introduction to Machine
More informationComputational Learning Theory
0. Computational Learning Theory Based on Machine Learning, T. Mitchell, McGRAW Hill, 1997, ch. 7 Acknowledgement: The present slides are an adaptation of slides drawn by T. Mitchell 1. Main Questions
More informationViolating the normal distribution assumption. So what do you do if the data are not normal and you still need to perform a test?
Violating the normal distribution assumption So what do you do if the data are not normal and you still need to perform a test? Remember, if your n is reasonably large, don t bother doing anything. Your
More informationICML '97 and AAAI '97 Tutorials
A Short Course in Computational Learning Theory: ICML '97 and AAAI '97 Tutorials Michael Kearns AT&T Laboratories Outline Sample Complexity/Learning Curves: nite classes, Occam's VC dimension Razor, Best
More informationComputational learning theory. PAC learning. VC dimension.
Computational learning theory. PAC learning. VC dimension. Petr Pošík Czech Technical University in Prague Faculty of Electrical Engineering Dept. of Cybernetics COLT 2 Concept...........................................................................................................
More informationA Geometric Approach to Statistical Learning Theory
A Geometric Approach to Statistical Learning Theory Shahar Mendelson Centre for Mathematics and its Applications The Australian National University Canberra, Australia What is a learning problem A class
More informationPart of the slides are adapted from Ziko Kolter
Part of the slides are adapted from Ziko Kolter OUTLINE 1 Supervised learning: classification........................................................ 2 2 Non-linear regression/classification, overfitting,
More informationReferences for online kernel methods
References for online kernel methods W. Liu, J. Principe, S. Haykin Kernel Adaptive Filtering: A Comprehensive Introduction. Wiley, 2010. W. Liu, P. Pokharel, J. Principe. The kernel least mean square
More informationA statistical learning approach to a problem of induction
A statistical learning approach to a problem of induction Kino Zhao yutingz3@uci.edu University of California, Irvine Logic and Philosophy of Science (Draft updated December 7, 2018) Abstract At its strongest,
More informationRecap from end of last time
Topics in Machine Learning Theory Avrim Blum 09/03/4 Lecture 3: Shifting/Sleeping Experts, the Winnow Algorithm, and L Margin Bounds Recap from end of last time RWM (multiplicative weights alg) p i = w
More informationMinimax risk bounds for linear threshold functions
CS281B/Stat241B (Spring 2008) Statistical Learning Theory Lecture: 3 Minimax risk bounds for linear threshold functions Lecturer: Peter Bartlett Scribe: Hao Zhang 1 Review We assume that there is a probability
More informationOnline Learning, Mistake Bounds, Perceptron Algorithm
Online Learning, Mistake Bounds, Perceptron Algorithm 1 Online Learning So far the focus of the course has been on batch learning, where algorithms are presented with a sample of training data, from which
More informationSupervised Machine Learning (Spring 2014) Homework 2, sample solutions
58669 Supervised Machine Learning (Spring 014) Homework, sample solutions Credit for the solutions goes to mainly to Panu Luosto and Joonas Paalasmaa, with some additional contributions by Jyrki Kivinen
More informationthe tree till a class assignment is reached
Decision Trees Decision Tree for Playing Tennis Prediction is done by sending the example down Prediction is done by sending the example down the tree till a class assignment is reached Definitions Internal
More information1 Review of Winnow Algorithm
COS 511: Theoretical Machine Learning Lecturer: Rob Schapire Lecture # 17 Scribe: Xingyuan Fang, Ethan April 9th, 2013 1 Review of Winnow Algorithm We have studied Winnow algorithm in Algorithm 1. Algorithm
More informationSmall sample size generalization
9th Scandinavian Conference on Image Analysis, June 6-9, 1995, Uppsala, Sweden, Preprint Small sample size generalization Robert P.W. Duin Pattern Recognition Group, Faculty of Applied Physics Delft University
More informationLecture 29: Computational Learning Theory
CS 710: Complexity Theory 5/4/2010 Lecture 29: Computational Learning Theory Instructor: Dieter van Melkebeek Scribe: Dmitri Svetlov and Jake Rosin Today we will provide a brief introduction to computational
More informationLecture 25 of 42. PAC Learning, VC Dimension, and Mistake Bounds
Lecture 25 of 42 PAC Learning, VC Dimension, and Mistake Bounds Thursday, 15 March 2007 William H. Hsu, KSU http://www.kddresearch.org/courses/spring2007/cis732 Readings: Sections 7.4.17.4.3, 7.5.17.5.3,
More informationPurposes of Data Analysis. Variables and Samples. Parameters and Statistics. Part 1: Probability Distributions
Part 1: Probability Distributions Purposes of Data Analysis True Distributions or Relationships in the Earths System Probability Distribution Normal Distribution Student-t Distribution Chi Square Distribution
More informationIntroduction to Machine Learning
Introduction to Machine Learning 236756 Prof. Nir Ailon Lecture 4: Computational Complexity of Learning & Surrogate Losses Efficient PAC Learning Until now we were mostly worried about sample complexity
More informationLearning Objectives. c D. Poole and A. Mackworth 2010 Artificial Intelligence, Lecture 7.2, Page 1
Learning Objectives At the end of the class you should be able to: identify a supervised learning problem characterize how the prediction is a function of the error measure avoid mixing the training and
More information