Universal Time-Series Forecasting with Mixture Predictors

1. Front Matter

   Pages i-viii

   PDF

2. Introduction

   • Daniil Ryabko

   Pages 1-10

3. Notation and Definitions

   • Daniil Ryabko

   Pages 11-16

4. Prediction in Total Variation: Characterizations

   • Daniil Ryabko

   Pages 17-22

5. Prediction in KL Divergence

   • Daniil Ryabko

   Pages 23-51

6. Decision-Theoretic Interpretations

   • Daniil Ryabko

   Pages 53-56

7. Middle-Case: Combining Predictors Whose Loss Vanishes

   • Daniil Ryabko

   Pages 57-65

8. Conditions Under Which One Measure Is a Predictor for Another

   • Daniil Ryabko

   Pages 67-76

9. Conclusion and Outlook

   • Daniil Ryabko

   Pages 77-82

10. Back Matter

    Pages 83-85

    PDF

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.

• Time Series
• Forecasting
• Bayesian Predictors
• Machine Learning Theory
• Statistics
• Information Theory
• Nonparametric Statistics

“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)

• Fishlife Research S.A., Belize City, Belize

  Daniil Ryabko

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

Policies and ethics