Find a copy online
Links to this item
ieeexplore.ieee.org Rutgers restricted Full text available from IEEE CISnet
Find a copy in the library
Finding libraries that hold this item...
Details
Genre/Form: | Online-Publikation |
---|---|
Material Type: | Internet resource |
Document Type: | Book, Internet Resource |
All Authors / Contributors: |
Peter D Grünwald |
ISBN: | 0262072815 9780262072816 |
OCLC Number: | 70292149 |
Description: | xxxii, 703 pages : illustrations ; 24 cm |
Contents: | 1. Learning, regularity, and compression -- 2. Probabilistic and statistical preliminaries -- 3. Information-theoretic preliminaries -- 4. Information-theoretic properties of statistical models -- 5. Crude two-part code MDL -- 6. Universal coding with countable models -- 7. Parametric models : normalized maximum likelihood -- 8. Parametric models : Bayes -- 9. Parametric models : prequential plug-in -- 10. Parametric models : two-part -- 11. NML with infinite complexity -- 12. Linear regression -- 13. Beyond parametrics -- 14. MDL model selection -- 15. MDL prediction and estimation -- 16. MDL consistency and convergence -- 17. MDL in context -- 18. The exponential or "maximum entropy" families -- 19. Information-theoretic properties of exponential families. |
Series Title: | Adaptive computation and machine learning. |
Responsibility: | Peter D. Grünwald. |
Abstract:
This introduction to the MDL Principle provides a reference accessible to graduate students and researchers in statistics, pattern classification, machine learning, and data mining, to philosophers interested in the foundations of statistics, and to researchers in other applied sciences that involve model selection.
Reviews

