Universal Time-Series Forecasting with Mixture Predictors / by Daniil Ryabko

By:

Ryabko, Daniil [VerfasserIn]

Resource type: Ressourcentyp: Buch (Online)Book (Online)Language: English Series: SpringerBriefs in Computer Science | Springer eBook CollectionPublisher: Cham : Springer International Publishing, 2020Publisher: Cham : Imprint: Springer, 2020Edition: 1st ed. 2020Description: 1 Online-Ressource(VIII, 85 p. 1 illus.)ISBN:

9783030543044

Subject(s):

Additional physical formats: 9783030543037 | 9783030543051 | Erscheint auch als: 9783030543037 Druck-Ausgabe | Erscheint auch als: 9783030543051 Druck-AusgabeDOI: DOI: 10.1007/978-3-030-54304-4Online resources:

Summary: 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.Summary: 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.PPN: PPN: 1734625228Package identifier: Produktsigel: ZDB-2-SCS | ZDB-2-SEB | ZDB-2-SXCS

Holdings ( 0 )

No physical items for this record