Universal Time-Series Forecasting with Mixture Predictors

by Daniil Ryabko

Overview

The author considers the problem of sequential probability forecasting in the most general setting, where the observed data may exhibit an arbitrary form of shastic 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.

Product Details

ISBN-13:	9783030543037
Publisher:	Springer International Publishing
Publication date:	09/27/2020
Series:	SpringerBriefs in Computer Science
Edition description:	1st ed. 2020
Pages:	85
Product dimensions:	6.10(w) x 9.25(h) x (d)

About the Author

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

Table of Contents

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.

Editorial Reviews

It is a very useful book for graduate students and researchers who are interested in the problem of sequential prediction.” (Lei Jin, Mathematical Reviews, November, 2022)

“The author lists some open problems in extending the subject matter discussed in the book. … The book … should be of interest for those researchers interested in the study of problems of sequential prediction.” (B. L. S. Prakasa Rao, zbMATH 1479.62002, 2022)

From the Publisher