The goal of learning theory is to approximate a function from sample values. To attain this goal learning theory draws on a variety of diverse subjects, specifically statistics, approximation theory, and algorithmics. Ideas from all these areas blended to form a subject whose many successful applications have triggered a rapid growth during the last two decades. This is the first book to give a general overview of the theoretical foundations of the subject emphasizing the approximation theory, while still giving a balanced overview. It is based on courses taught by the authors, and is reasonably self-contained so will appeal to a broad spectrum of researchers in learning theory and adjacent fields. It will also serve as an introduction for graduate students and others entering the field, who wish to see how the problems raised in learning theory relate to other disciplines.
• Balanced view, with rigorous approach to issues of practical importance • First book to adopt the approximation theory viewpoint • Will appeal to mathematicians as well as statisticians and computer scientists
Contents
Preface; Foreword; 1. The framework of learning; 2. Basic hypothesis spaces; 3. Estimating the sample error; 4. Polynomial decay approximation error; 5. Estimating covering numbers; 6. Logarithmic decay approximation error; 7. On the bias-variance problem; 8. Regularization; 9. Support vector machines for classification; 10. General regularized classifiers; Bibliography; Index.
Printer friendly version
Email a colleague