Universal Time-Series Forecasting with Mixture Predictors

1. Auflage 2020
ISBN: 978-3-030-54303-7
Verlag: Springer International Publishing

Buch, Englisch, 85 Seiten, Format (B × H): 155 mm x 235 mm, Gewicht: 160 g

Reihe: SpringerBriefs in Computer Science

The author considers the problem of sequential probability forecasting in the most general setting, where the observed data may exhibit an arbitrary form of stochastic dependence. All the results presented are theoretical, but they concern the foundations of some problems in such applied areas as machine learning, information theory and data compression.

Zielgruppe

Research

Autoren/Hrsg.

Ryabko, Daniil

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Mathematik für Informatiker
• Interdisziplinäres Wissenschaften Wissenschaften: Forschung und Information Informationstheorie, Kodierungstheorie
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
• Mathematik | Informatik EDV | Informatik Daten / Datenbanken Informationstheorie, Kodierungstheorie
• Mathematik | Informatik EDV | Informatik Informatik Theoretische Informatik

Inhaltsverzeichnis

Introduction.- Notation and Definitions.- Prediction in Total Variation: Characterizations.- Prediction in KL-Divergence.- Decision-Theoretic Interpretations.- Middle-Case: Combining Predictors Whose Loss Vanishes.- Conditions Under Which One Measure Is a Predictor for Another.- Conclusion and Outlook.

Über Autor(innen)

Dr. Daniil Ryabko (HDR) has a full-time position at INRIA, he has recently been on research assignments in Belize and Madagascar.