- Title Pages
- Series Foreword
- Preface
-
1 Introduction to Semi-Supervised Learning -
1 A Taxonomy for Semi-Supervised Learning Methods -
3 Semi-Supervised Text Classification Using EM -
4 Risks of Semi-Supervised Learning: How Unlabeled Data Can Degrade Performance of Generative Classifiers -
5 Probabilistic Semi-Supervised Clustering with Constraints -
6 Transductive Support Vector Machines -
7 Semi-Supervised Learning Using Semi-Definite Programming -
8 Gaussian Processes and the Null-Category Noise Model -
9 Entropy Regularization -
10 Data-Dependent Regularization -
11 Label Propagation and Quadratic Criterion -
12 The Geometric Basis of Semi-Supervised Learning -
13 Discrete Regularization -
14 Semi-Supervised Learning with Conditional Harmonic Mixing -
15 Graph Kernels by Spectral Transforms -
16 Spectral Methods for Dimensionality Reduction -
17 Modifying Distances -
18 Large-Scale Algorithms -
19 Semi-Supervised Protein Classification Using Cluster Kernels -
20 Prediction of Protein Function from Networks -
25 Analysis of Benchmarks -
22 An Augmented PAC Model for Semi-Supervised Learning -
23 Metric-Based Approaches for Semi-Supervised Regression and Classification -
24 Transductive Inference and Semi-Supervised Learning -
25 A Discussion of Semi-Supervised Learning and Transduction - References
- Notation and Symbols
- Contributors
- Index
An Augmented PAC Model for Semi-Supervised Learning
An Augmented PAC Model for Semi-Supervised Learning
- Chapter:
- (p.396) (p.397) 22 An Augmented PAC Model for Semi-Supervised Learning
- Source:
- Semi-Supervised Learning
- Author(s):
Balcan Maria-Florina
Blum Avrim
- Publisher:
- The MIT Press
This chapter describes an augmented version of the PAC model, designed with semi-supervised learning in mind, that can be used to help think about the problem of learning from labeled and unlabeled data and many of the different approaches taken. The model provides a unified framework for analyzing when and why unlabeled data can help, in which one can discuss both sample-complexity and algorithmic issues. The model described here can be viewed as an extension of the standard PAC model, where a compatibility function is also proposed—a type of compatibility that one believes the target concept should have with the underlying distribution of data. Unlabeled data are potentially helpful in this setting because they allow one to estimate compatibility over the space of hypotheses.
Keywords: PAC model, semi-supervised learning, problem of learning, unlabeled data, sample-complexity, algorithmic issues, compatibility function
MIT Press Scholarship Online requires a subscription or purchase to access the full text of books within the service. Public users can however freely search the site and view the abstracts and keywords for each book and chapter.
Please, subscribe or login to access full text content.
If you think you should have access to this title, please contact your librarian.
To troubleshoot, please check our FAQs, and if you can't find the answer there, please contact us.
- Title Pages
- Series Foreword
- Preface
-
1 Introduction to Semi-Supervised Learning -
1 A Taxonomy for Semi-Supervised Learning Methods -
3 Semi-Supervised Text Classification Using EM -
4 Risks of Semi-Supervised Learning: How Unlabeled Data Can Degrade Performance of Generative Classifiers -
5 Probabilistic Semi-Supervised Clustering with Constraints -
6 Transductive Support Vector Machines -
7 Semi-Supervised Learning Using Semi-Definite Programming -
8 Gaussian Processes and the Null-Category Noise Model -
9 Entropy Regularization -
10 Data-Dependent Regularization -
11 Label Propagation and Quadratic Criterion -
12 The Geometric Basis of Semi-Supervised Learning -
13 Discrete Regularization -
14 Semi-Supervised Learning with Conditional Harmonic Mixing -
15 Graph Kernels by Spectral Transforms -
16 Spectral Methods for Dimensionality Reduction -
17 Modifying Distances -
18 Large-Scale Algorithms -
19 Semi-Supervised Protein Classification Using Cluster Kernels -
20 Prediction of Protein Function from Networks -
25 Analysis of Benchmarks -
22 An Augmented PAC Model for Semi-Supervised Learning -
23 Metric-Based Approaches for Semi-Supervised Regression and Classification -
24 Transductive Inference and Semi-Supervised Learning -
25 A Discussion of Semi-Supervised Learning and Transduction - References
- Notation and Symbols
- Contributors
- Index
