The Nature of Statistical Learning Theory

1. Front Matter

   Pages i-xv

   PDF

2. Introduction: Four Periods in the Research of the Learning Problem

   • Vladimir N. Vapnik

   Pages 1-14

3. Setting of the Learning Problem

   • Vladimir N. Vapnik

   Pages 15-32

4. Consistency of Learning Processes

   • Vladimir N. Vapnik

   Pages 33-64

5. Bounds on the Rate of Convergence of Learning Processes

   • Vladimir N. Vapnik

   Pages 65-87

6. Controlling the Generalization Ability of Learning Processes

   • Vladimir N. Vapnik

   Pages 89-118

7. Constructing Learning Algorithms

   • Vladimir N. Vapnik

   Pages 119-166

8. Conclusion: What is Important in Learning Theory?

   • Vladimir N. Vapnik

   Pages 167-175

9. Back Matter

   Pages 177-188

   PDF

The aim of this book is to discuss the fundamental ideas which lie behind the statistical theory of learning and generalization. It considers learning from the general point of view of function estimation based on empirical data. Omitting proofs and technical details, the author concentrates on discussing the main results of learning theory and their connections to fundamental problems in statistics. These include: - the general setting of learning problems and the general model of minimizing the risk functional from empirical data - a comprehensive analysis of the empirical risk minimization principle and shows how this allows for the construction of necessary and sufficient conditions for consistency - non-asymptotic bounds for the risk achieved using the empirical risk minimization principle - principles for controlling the generalization ability of learning machines using small sample sizes - introducing a new type of universal learning machine that controls the generalization ability.

• Statistica
• algorithms
• boundary element method
• construction
• controlling
• convergence
• function
• functional
• learning
• learning algorithm
• learning theory
• model
• proof
• statistical theory
• statistics

"This interesting book helps a reader to understand the interconnections between various streams in the empirical modeling realm and may be recommended to any reader who feels lost in modern terminology." V.V. Fedorov, Oak Ridge National Laboratory, USA

• AT&T Bell Laboratories, Holmdel, USA

  Vladimir N. Vapnik

Policies and ethics