User-friendly Introduction to PAC-Bayes Bounds - Pierre Alquier

User-friendly Introduction to PAC-Bayes Bounds

(Autor)

Buch | Softcover
144 Seiten
2024
now publishers Inc (Verlag)
978-1-63828-326-3 (ISBN)
99,95 inkl. MwSt
Probably almost correct (PAC) bounds have been an intensive field of research over the last two decades. In this tutorial, the author guides the reader through the topic’s complexity and large body of publications. Covering both empirical and oracle PAC-bounds, this book is a primer for those who want to get to grips quickly with the subject.
Probably almost correct (PAC) bounds have been an intensive field of research over the last two decades. Hundreds of papers have been published and much progress has been made resulting in PAC-Bayes bounds becoming an important technique in machine learning.The proliferation of research has made the field for a newcomer somewhat daunting. In this tutorial, the author guides the reader through the topic’s complexity and large body of publications. Covering both empirical and oracle PAC-bounds, this book serves as a primer for students and researchers who want to get to grips quickly with the subject. It provides a friendly introduction that illuminates the basic theory and points to the most important publications to gain deeper understanding of any particular aspect.

1. Introduction
2. First Step in the PAC-Bayes World
3. Tight and Non-vacuous PAC-Bayes Bounds
4. PAC-Bayes Oracle Inequalities and Fast Rates
5. Beyond “Bounded Loss” and “i.i.d. Observations”
6. Related Approaches in Statistics and Machine Learning Theory
7. Conclusion
Acknowledgements
References

Erscheinungsdatum
Reihe/Serie Foundations and Trends® in Machine Learning
Verlagsort Hanover
Sprache englisch
Maße 156 x 234 mm
Gewicht 213 g
Themenwelt Informatik Theorie / Studium Künstliche Intelligenz / Robotik
ISBN-10 1-63828-326-5 / 1638283265
ISBN-13 978-1-63828-326-3 / 9781638283263
Zustand Neuware
Haben Sie eine Frage zum Produkt?
Mehr entdecken
aus dem Bereich
von absurd bis tödlich: Die Tücken der künstlichen Intelligenz

von Katharina Zweig

Buch | Softcover (2023)
Heyne (Verlag)
20,00
dem Menschen überlegen – wie KI uns rettet und bedroht

von Manfred Spitzer

Buch | Hardcover (2023)
Droemer (Verlag)
24,00