SlideShare uma empresa Scribd logo
1 de 15
Baixar para ler offline
A Theory of the Learnable
Leslie Valiant
Dhruv Gairola
Computational Complexity, Michael Soltys
gairold@mcmaster.ca ; dhruvgairola.blogspot.ca

November 13, 2013

Dhruv Gairola (McMaster Univ.)

A Theory of the Learnable

November 13, 2013

1 / 15
Overview

1

Learning

2

Contribution

3

PAC learning
Sample complexity
Boolean functions
k-decision lists

4

Conclusion

Dhruv Gairola (McMaster Univ.)

A Theory of the Learnable

November 13, 2013

2 / 15
Learning

Humans can learn.
Machine learning (ML) : learning from data; knowledge acquisition
w/o explicit programming.
Explore computational models for learning.
Use models to get insights about learning.
Use models to develop new learning algorithms.

Dhruv Gairola (McMaster Univ.)

A Theory of the Learnable

November 13, 2013

3 / 15
Modelling supervised Learning

Given training set of labelled examples, learning algorithm generates a
hypothesis (candidate function). Run hypothesis on test set to check
how good it is.
But how good really? Maybe training and test data consists of bad
examples so the hypothesis doesn’t generalize well.
Insight : Introduce probabilities to measure degree of certainty and
correctness.

Dhruv Gairola (McMaster Univ.)

A Theory of the Learnable

November 13, 2013

4 / 15
Contribution

With high probability an (efficient) learning algorithm will find a
hypothesis that is approximately identical to the hidden target
function.
Intuition : A hypothesis built from a large amount of training data is
unlikely to be wrong i.e., Probably approximately correct (PAC).

Dhruv Gairola (McMaster Univ.)

A Theory of the Learnable

November 13, 2013

5 / 15
PAC learning

Goal : show that after training, with high probability, all good
hypothesis will be approximately correct.
Notation :
X : set of all possible examples
D : distribution from which examples are drawn
H : set of all possible hypothesis
N : |Xtraining |
f : target function

Dhruv Gairola (McMaster Univ.)

A Theory of the Learnable

November 13, 2013

6 / 15
PAC learning (2)

Hypothesis hg ∈ H is approximately correct if :
error (hg ) ≤ where
error(h) = P(h(x) = f (x)| x drawn from D)

Bad hypothesis :
error (hb ) >
P(hb disagrees with 1 example) >

Dhruv Gairola (McMaster Univ.)

A Theory of the Learnable

November 13, 2013

7 / 15
PAC learning (3)

P(hb agrees with 1 example) ≤ (1 − ).
P(hb agrees with N examples) ≤ (1 − )N .
P(Hb contains a good hypothesis) ≤ |Hb |(1 − )N ≤ |H|(1 − )N .
Lets say |H|(1 − )N ≤ δ.
...
N ≥ ( 1 )(ln 1 + ln|H|)
δ
This expresses sample complexity.

Dhruv Gairola (McMaster Univ.)

A Theory of the Learnable

November 13, 2013

8 / 15
Sample complexity

N ≥ ( 1 )(ln 1 + ln|H|)
δ
If you train the learning algo with Xtraining of size N, then the
returned hypothesis is PAC because there exists a probability (1 − δ)
that this hypothesis will have an error of at most (approximately).
e.g., if you want smaller and smaller δ, you need more N’s (more
examples).
Lets look at example of H : boolean functions.

Dhruv Gairola (McMaster Univ.)

A Theory of the Learnable

November 13, 2013

9 / 15
Why boolean functions?

Because boolean functions can represent concepts, which is what we
commonly want machines to learn.
Concepts are predicates e.g., isMaleOrFemale(height).

Dhruv Gairola (McMaster Univ.)

A Theory of the Learnable

November 13, 2013

10 / 15
Boolean functions

Boolean functions are of the form f : {0, 1}n → {0, 1} where n are
the number of literals.
n

Let H = {all boolean functions on n literals} ∴ |H| = 22

Substituting H into sample complexity expression gives O(2n ) i.e.,
boolean functions are not PAC-learnable.
Can we restrict size of H?

Dhruv Gairola (McMaster Univ.)

A Theory of the Learnable

November 13, 2013

11 / 15
k-decision lists

A single decision list (DL) is a representation of a single boolean
function. DL is not PAC-learnable either.
A single DL consists of a series of tests.
e.g. if f1 then return b1 ; elseif f2 then return b2 ; ... elseif fn return bn ;
A single DL corresponds to a single hypothesis.
Apply restriction : A k-decision list is a decision list where each test is
a conjunction of at most k literals.

Dhruv Gairola (McMaster Univ.)

A Theory of the Learnable

November 13, 2013

12 / 15
k-decision lists (2)

What is |H| for k-DL i.e., what is |k-DL(n)| where n is number of
literals?
k
k
After calculations, |k-DL(n)| = 2O(n log (n ))
Substitute |k-DL(n)| into sample complexity expression :
N ≥ 1 (ln 1 + O(nk log (nk )))
δ
δ
Sample complexity is poly! What about learning complexity?
There are efficient algorithms for learning k-decision lists! (e.g.,
greedy algorithm)
We have polynomial sample complexity and efficient k-DL algorithms
∴ k-DL is PAC learnable!

Dhruv Gairola (McMaster Univ.)

A Theory of the Learnable

November 13, 2013

13 / 15
Conclusion

PAC learning : with high
probability an (efficient)
learning algorithm will find a
hypothesis that is
approximately identical to
the hidden target hypothesis.
k-DL is PAC learnable.
Computational learning
theory : concerned with the
analysis of ML algorithms
and covers a lot of fields.

Dhruv Gairola (McMaster Univ.)

A Theory of the Learnable

November 13, 2013

14 / 15
References

Carla Gomes, Cornell, Foundations of AI notes

Dhruv Gairola (McMaster Univ.)

A Theory of the Learnable

November 13, 2013

15 / 15

Mais conteúdo relacionado

Mais procurados

Moment generating function
Moment generating functionMoment generating function
Moment generating functioneddyboadu
 
Reinforcement learning.pptx
Reinforcement learning.pptxReinforcement learning.pptx
Reinforcement learning.pptxaniketgupta16440
 
Chapter 19 decision-making under risk
Chapter 19   decision-making under riskChapter 19   decision-making under risk
Chapter 19 decision-making under riskBich Lien Pham
 
ZK Study Club: Sumcheck Arguments and Their Applications
ZK Study Club: Sumcheck Arguments and Their ApplicationsZK Study Club: Sumcheck Arguments and Their Applications
ZK Study Club: Sumcheck Arguments and Their ApplicationsAlex Pruden
 
Particle Filter Tracking in Python
Particle Filter Tracking in PythonParticle Filter Tracking in Python
Particle Filter Tracking in PythonKohta Ishikawa
 
Data 101: Introduction to Data Visualization
Data 101:  Introduction to Data VisualizationData 101:  Introduction to Data Visualization
Data 101: Introduction to Data VisualizationDavid Newbury
 
Network Analytics - Homework 3 - Msc Business Analytics - Imperial College Lo...
Network Analytics - Homework 3 - Msc Business Analytics - Imperial College Lo...Network Analytics - Homework 3 - Msc Business Analytics - Imperial College Lo...
Network Analytics - Homework 3 - Msc Business Analytics - Imperial College Lo...Jonathan Zimmermann
 
Discrete mathematics Ch2 Propositional Logic_Dr.khaled.Bakro د. خالد بكرو
Discrete mathematics Ch2 Propositional Logic_Dr.khaled.Bakro د. خالد بكروDiscrete mathematics Ch2 Propositional Logic_Dr.khaled.Bakro د. خالد بكرو
Discrete mathematics Ch2 Propositional Logic_Dr.khaled.Bakro د. خالد بكروDr. Khaled Bakro
 
02 Machine Learning - Introduction probability
02 Machine Learning - Introduction probability02 Machine Learning - Introduction probability
02 Machine Learning - Introduction probabilityAndres Mendez-Vazquez
 
2.6 support vector machines and associative classifiers revised
2.6 support vector machines and associative classifiers revised2.6 support vector machines and associative classifiers revised
2.6 support vector machines and associative classifiers revisedKrish_ver2
 
Logic
LogicLogic
LogicHamxi
 
Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...
Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...
Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...Universitat Politècnica de Catalunya
 

Mais procurados (20)

Moment generating function
Moment generating functionMoment generating function
Moment generating function
 
Reinforcement learning.pptx
Reinforcement learning.pptxReinforcement learning.pptx
Reinforcement learning.pptx
 
Stochastic calculus
Stochastic calculus Stochastic calculus
Stochastic calculus
 
Heuristic search
Heuristic searchHeuristic search
Heuristic search
 
Lecture10 - Naïve Bayes
Lecture10 - Naïve BayesLecture10 - Naïve Bayes
Lecture10 - Naïve Bayes
 
Chapter 19 decision-making under risk
Chapter 19   decision-making under riskChapter 19   decision-making under risk
Chapter 19 decision-making under risk
 
Continuous distributions
Continuous distributionsContinuous distributions
Continuous distributions
 
The Stable Marriage Problem
The Stable Marriage ProblemThe Stable Marriage Problem
The Stable Marriage Problem
 
ZK Study Club: Sumcheck Arguments and Their Applications
ZK Study Club: Sumcheck Arguments and Their ApplicationsZK Study Club: Sumcheck Arguments and Their Applications
ZK Study Club: Sumcheck Arguments and Their Applications
 
Particle Filter Tracking in Python
Particle Filter Tracking in PythonParticle Filter Tracking in Python
Particle Filter Tracking in Python
 
たのしい関数型
たのしい関数型たのしい関数型
たのしい関数型
 
Naive Bayes Presentation
Naive Bayes PresentationNaive Bayes Presentation
Naive Bayes Presentation
 
Data 101: Introduction to Data Visualization
Data 101:  Introduction to Data VisualizationData 101:  Introduction to Data Visualization
Data 101: Introduction to Data Visualization
 
Network Analytics - Homework 3 - Msc Business Analytics - Imperial College Lo...
Network Analytics - Homework 3 - Msc Business Analytics - Imperial College Lo...Network Analytics - Homework 3 - Msc Business Analytics - Imperial College Lo...
Network Analytics - Homework 3 - Msc Business Analytics - Imperial College Lo...
 
Discrete mathematics Ch2 Propositional Logic_Dr.khaled.Bakro د. خالد بكرو
Discrete mathematics Ch2 Propositional Logic_Dr.khaled.Bakro د. خالد بكروDiscrete mathematics Ch2 Propositional Logic_Dr.khaled.Bakro د. خالد بكرو
Discrete mathematics Ch2 Propositional Logic_Dr.khaled.Bakro د. خالد بكرو
 
02 Machine Learning - Introduction probability
02 Machine Learning - Introduction probability02 Machine Learning - Introduction probability
02 Machine Learning - Introduction probability
 
2.6 support vector machines and associative classifiers revised
2.6 support vector machines and associative classifiers revised2.6 support vector machines and associative classifiers revised
2.6 support vector machines and associative classifiers revised
 
Logic
LogicLogic
Logic
 
Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...
Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...
Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...
 
Chapter1p1
Chapter1p1Chapter1p1
Chapter1p1
 

Semelhante a A Theory of the Learnable; PAC Learning

Data.Mining.C.6(II).classification and prediction
Data.Mining.C.6(II).classification and predictionData.Mining.C.6(II).classification and prediction
Data.Mining.C.6(II).classification and predictionMargaret Wang
 
Latent Dirichlet Allocation
Latent Dirichlet AllocationLatent Dirichlet Allocation
Latent Dirichlet AllocationMarco Righini
 
Lecture 3 (Supervised learning)
Lecture 3 (Supervised learning)Lecture 3 (Supervised learning)
Lecture 3 (Supervised learning)VARUN KUMAR
 
Сергей Кольцов —НИУ ВШЭ —ICBDA 2015
Сергей Кольцов —НИУ ВШЭ —ICBDA 2015Сергей Кольцов —НИУ ВШЭ —ICBDA 2015
Сергей Кольцов —НИУ ВШЭ —ICBDA 2015rusbase
 
Basic review on topic modeling
Basic review on  topic modelingBasic review on  topic modeling
Basic review on topic modelingHiroyuki Kuromiya
 
Bayesian Hierarchical Models
Bayesian Hierarchical ModelsBayesian Hierarchical Models
Bayesian Hierarchical ModelsAmmar Rashed
 
PAGOdA poster
PAGOdA posterPAGOdA poster
PAGOdA posterDBOnto
 
2.7 other classifiers
2.7 other classifiers2.7 other classifiers
2.7 other classifiersKrish_ver2
 
A new generalized lindley distribution
A new generalized lindley distributionA new generalized lindley distribution
A new generalized lindley distributionAlexander Decker
 
Introduction to machine learning
Introduction to machine learningIntroduction to machine learning
Introduction to machine learningbutest
 
Linear Discriminant Analysis and Its Generalization
Linear Discriminant Analysis and Its GeneralizationLinear Discriminant Analysis and Its Generalization
Linear Discriminant Analysis and Its Generalization일상 온
 
Deep Domain Adaptation using Adversarial Learning and GAN
Deep Domain Adaptation using Adversarial Learning and GAN Deep Domain Adaptation using Adversarial Learning and GAN
Deep Domain Adaptation using Adversarial Learning and GAN RishirajChakraborty4
 
Matrix Completion Presentation
Matrix Completion PresentationMatrix Completion Presentation
Matrix Completion PresentationMichael Hankin
 

Semelhante a A Theory of the Learnable; PAC Learning (20)

Data.Mining.C.6(II).classification and prediction
Data.Mining.C.6(II).classification and predictionData.Mining.C.6(II).classification and prediction
Data.Mining.C.6(II).classification and prediction
 
PRIMES is in P
PRIMES is in PPRIMES is in P
PRIMES is in P
 
Latent Dirichlet Allocation
Latent Dirichlet AllocationLatent Dirichlet Allocation
Latent Dirichlet Allocation
 
pres_coconat
pres_coconatpres_coconat
pres_coconat
 
Lecture 3 (Supervised learning)
Lecture 3 (Supervised learning)Lecture 3 (Supervised learning)
Lecture 3 (Supervised learning)
 
Сергей Кольцов —НИУ ВШЭ —ICBDA 2015
Сергей Кольцов —НИУ ВШЭ —ICBDA 2015Сергей Кольцов —НИУ ВШЭ —ICBDA 2015
Сергей Кольцов —НИУ ВШЭ —ICBDA 2015
 
Basic review on topic modeling
Basic review on  topic modelingBasic review on  topic modeling
Basic review on topic modeling
 
Bayesian Hierarchical Models
Bayesian Hierarchical ModelsBayesian Hierarchical Models
Bayesian Hierarchical Models
 
ppt
pptppt
ppt
 
PAGOdA poster
PAGOdA posterPAGOdA poster
PAGOdA poster
 
Chapter1p2.pptx
Chapter1p2.pptxChapter1p2.pptx
Chapter1p2.pptx
 
Chapter1p2.pptx
Chapter1p2.pptxChapter1p2.pptx
Chapter1p2.pptx
 
2.7 other classifiers
2.7 other classifiers2.7 other classifiers
2.7 other classifiers
 
Day 3 SPSS
Day 3 SPSSDay 3 SPSS
Day 3 SPSS
 
A new generalized lindley distribution
A new generalized lindley distributionA new generalized lindley distribution
A new generalized lindley distribution
 
Introduction to machine learning
Introduction to machine learningIntroduction to machine learning
Introduction to machine learning
 
Linear Discriminant Analysis and Its Generalization
Linear Discriminant Analysis and Its GeneralizationLinear Discriminant Analysis and Its Generalization
Linear Discriminant Analysis and Its Generalization
 
Deep Learning Opening Workshop - Horseshoe Regularization for Machine Learnin...
Deep Learning Opening Workshop - Horseshoe Regularization for Machine Learnin...Deep Learning Opening Workshop - Horseshoe Regularization for Machine Learnin...
Deep Learning Opening Workshop - Horseshoe Regularization for Machine Learnin...
 
Deep Domain Adaptation using Adversarial Learning and GAN
Deep Domain Adaptation using Adversarial Learning and GAN Deep Domain Adaptation using Adversarial Learning and GAN
Deep Domain Adaptation using Adversarial Learning and GAN
 
Matrix Completion Presentation
Matrix Completion PresentationMatrix Completion Presentation
Matrix Completion Presentation
 

Mais de dhruvgairola

A Generic Algebraic Model for the Analysis of Cryptographic Key Assignment Sc...
A Generic Algebraic Model for the Analysis of Cryptographic Key Assignment Sc...A Generic Algebraic Model for the Analysis of Cryptographic Key Assignment Sc...
A Generic Algebraic Model for the Analysis of Cryptographic Key Assignment Sc...dhruvgairola
 
Differences bet. versions of UML diagrams.
Differences bet. versions of UML diagrams.Differences bet. versions of UML diagrams.
Differences bet. versions of UML diagrams.dhruvgairola
 
Discussion : Info sharing across private DBs
Discussion : Info sharing across private DBsDiscussion : Info sharing across private DBs
Discussion : Info sharing across private DBsdhruvgairola
 

Mais de dhruvgairola (7)

A Generic Algebraic Model for the Analysis of Cryptographic Key Assignment Sc...
A Generic Algebraic Model for the Analysis of Cryptographic Key Assignment Sc...A Generic Algebraic Model for the Analysis of Cryptographic Key Assignment Sc...
A Generic Algebraic Model for the Analysis of Cryptographic Key Assignment Sc...
 
Differences bet. versions of UML diagrams.
Differences bet. versions of UML diagrams.Differences bet. versions of UML diagrams.
Differences bet. versions of UML diagrams.
 
Beginning jQuery
Beginning jQueryBeginning jQuery
Beginning jQuery
 
Beginning CSS.
Beginning CSS.Beginning CSS.
Beginning CSS.
 
Discussion : Info sharing across private DBs
Discussion : Info sharing across private DBsDiscussion : Info sharing across private DBs
Discussion : Info sharing across private DBs
 
Ajax
AjaxAjax
Ajax
 
Potters wheel
Potters wheelPotters wheel
Potters wheel
 

Último

Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfHyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfPrecisely
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyAlfredo García Lavilla
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenHervé Boutemy
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024Lonnie McRorey
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Manik S Magar
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .Alan Dix
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piececharlottematthew16
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DaySri Ambati
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionDilum Bandara
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 

Último (20)

Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfHyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easy
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache Maven
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An Introduction
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 

A Theory of the Learnable; PAC Learning

  • 1. A Theory of the Learnable Leslie Valiant Dhruv Gairola Computational Complexity, Michael Soltys gairold@mcmaster.ca ; dhruvgairola.blogspot.ca November 13, 2013 Dhruv Gairola (McMaster Univ.) A Theory of the Learnable November 13, 2013 1 / 15
  • 2. Overview 1 Learning 2 Contribution 3 PAC learning Sample complexity Boolean functions k-decision lists 4 Conclusion Dhruv Gairola (McMaster Univ.) A Theory of the Learnable November 13, 2013 2 / 15
  • 3. Learning Humans can learn. Machine learning (ML) : learning from data; knowledge acquisition w/o explicit programming. Explore computational models for learning. Use models to get insights about learning. Use models to develop new learning algorithms. Dhruv Gairola (McMaster Univ.) A Theory of the Learnable November 13, 2013 3 / 15
  • 4. Modelling supervised Learning Given training set of labelled examples, learning algorithm generates a hypothesis (candidate function). Run hypothesis on test set to check how good it is. But how good really? Maybe training and test data consists of bad examples so the hypothesis doesn’t generalize well. Insight : Introduce probabilities to measure degree of certainty and correctness. Dhruv Gairola (McMaster Univ.) A Theory of the Learnable November 13, 2013 4 / 15
  • 5. Contribution With high probability an (efficient) learning algorithm will find a hypothesis that is approximately identical to the hidden target function. Intuition : A hypothesis built from a large amount of training data is unlikely to be wrong i.e., Probably approximately correct (PAC). Dhruv Gairola (McMaster Univ.) A Theory of the Learnable November 13, 2013 5 / 15
  • 6. PAC learning Goal : show that after training, with high probability, all good hypothesis will be approximately correct. Notation : X : set of all possible examples D : distribution from which examples are drawn H : set of all possible hypothesis N : |Xtraining | f : target function Dhruv Gairola (McMaster Univ.) A Theory of the Learnable November 13, 2013 6 / 15
  • 7. PAC learning (2) Hypothesis hg ∈ H is approximately correct if : error (hg ) ≤ where error(h) = P(h(x) = f (x)| x drawn from D) Bad hypothesis : error (hb ) > P(hb disagrees with 1 example) > Dhruv Gairola (McMaster Univ.) A Theory of the Learnable November 13, 2013 7 / 15
  • 8. PAC learning (3) P(hb agrees with 1 example) ≤ (1 − ). P(hb agrees with N examples) ≤ (1 − )N . P(Hb contains a good hypothesis) ≤ |Hb |(1 − )N ≤ |H|(1 − )N . Lets say |H|(1 − )N ≤ δ. ... N ≥ ( 1 )(ln 1 + ln|H|) δ This expresses sample complexity. Dhruv Gairola (McMaster Univ.) A Theory of the Learnable November 13, 2013 8 / 15
  • 9. Sample complexity N ≥ ( 1 )(ln 1 + ln|H|) δ If you train the learning algo with Xtraining of size N, then the returned hypothesis is PAC because there exists a probability (1 − δ) that this hypothesis will have an error of at most (approximately). e.g., if you want smaller and smaller δ, you need more N’s (more examples). Lets look at example of H : boolean functions. Dhruv Gairola (McMaster Univ.) A Theory of the Learnable November 13, 2013 9 / 15
  • 10. Why boolean functions? Because boolean functions can represent concepts, which is what we commonly want machines to learn. Concepts are predicates e.g., isMaleOrFemale(height). Dhruv Gairola (McMaster Univ.) A Theory of the Learnable November 13, 2013 10 / 15
  • 11. Boolean functions Boolean functions are of the form f : {0, 1}n → {0, 1} where n are the number of literals. n Let H = {all boolean functions on n literals} ∴ |H| = 22 Substituting H into sample complexity expression gives O(2n ) i.e., boolean functions are not PAC-learnable. Can we restrict size of H? Dhruv Gairola (McMaster Univ.) A Theory of the Learnable November 13, 2013 11 / 15
  • 12. k-decision lists A single decision list (DL) is a representation of a single boolean function. DL is not PAC-learnable either. A single DL consists of a series of tests. e.g. if f1 then return b1 ; elseif f2 then return b2 ; ... elseif fn return bn ; A single DL corresponds to a single hypothesis. Apply restriction : A k-decision list is a decision list where each test is a conjunction of at most k literals. Dhruv Gairola (McMaster Univ.) A Theory of the Learnable November 13, 2013 12 / 15
  • 13. k-decision lists (2) What is |H| for k-DL i.e., what is |k-DL(n)| where n is number of literals? k k After calculations, |k-DL(n)| = 2O(n log (n )) Substitute |k-DL(n)| into sample complexity expression : N ≥ 1 (ln 1 + O(nk log (nk ))) δ δ Sample complexity is poly! What about learning complexity? There are efficient algorithms for learning k-decision lists! (e.g., greedy algorithm) We have polynomial sample complexity and efficient k-DL algorithms ∴ k-DL is PAC learnable! Dhruv Gairola (McMaster Univ.) A Theory of the Learnable November 13, 2013 13 / 15
  • 14. Conclusion PAC learning : with high probability an (efficient) learning algorithm will find a hypothesis that is approximately identical to the hidden target hypothesis. k-DL is PAC learnable. Computational learning theory : concerned with the analysis of ML algorithms and covers a lot of fields. Dhruv Gairola (McMaster Univ.) A Theory of the Learnable November 13, 2013 14 / 15
  • 15. References Carla Gomes, Cornell, Foundations of AI notes Dhruv Gairola (McMaster Univ.) A Theory of the Learnable November 13, 2013 15 / 15