Universal Time-Series Forecasting with Mixture Predictors [Paperback]

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.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.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)Dr. Daniil Ryabko (HDR) has a full-time position at INRIA, he has recently been on research assignments in Belize and Madagascar.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.Considers problem of sequential probability forecasting in the most general setting Results presented concern the foundations of problems in areas such as machine learning, information theory and data compression Material presented in a way that assumes familiarity with basic concepts of probability and statistics