Universal Time-Series Forecasting with Mixture Predictors

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.

Autorentext

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

Zusammenfassung
"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)

Inhalt
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.