Prediction, learning, and games / Nicolo Cesa-Bianchi, Gabor Lugosi.
"This important new text and reference for researchers and students in machine learning, game theory, statistics, and information theory offers the first comprehensive treatment of the problem of predicting individual sequences. Unlike standard statistical approaches to forecasting, prediction...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Book |
| Language: | English |
| Published: |
Cambridge ; New York :
Cambridge University Press,
2006.
|
| Subjects: |
| Summary: | "This important new text and reference for researchers and students in machine learning, game theory, statistics, and information theory offers the first comprehensive treatment of the problem of predicting individual sequences. Unlike standard statistical approaches to forecasting, prediction of individual sequences does not impose any probabilistic assumption on the data-generating mechanism. Yet, prediction algorithms can be constructed that work well for all possible sequences, in the sense that their performance is always nearly as good as the best forecasting strategy in a given reference class."--BOOK JACKET. |
|---|---|
| Physical Description: | xii, 394 pages : illustrations ; 27 cm |
| Bibliography: | Includes bibliographical references (pages 373-386) and index. |
| ISBN: | 0521841089 9780521841085 |