國立高雄大學圖資館 |

Language: English

Back

Universal time-series forecasting wi...

Ryabko, Daniil.

Universal time-series forecasting with mixture predictors

Record Type:	Electronic resources : Monograph/item
Title/Author:	Universal time-series forecasting with mixture predictorsby Daniil Ryabko.
Author:	Ryabko, Daniil.
Published:	Cham :Springer International Publishing :2020.
Description:	viii, 85 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
Subject:	Time-series analysisData processing.
Online resource:	https://doi.org/10.1007/978-3-030-54304-4
ISBN:	9783030543044$q(electronic bk.)

Universal time-series forecasting with mixture predictors
Ryabko, Daniil.

Universal time-series forecasting with mixture predictors[electronic resource] /by Daniil Ryabko. - Cham :Springer International Publishing :2020. - viii, 85 p. :ill., digital ;24 cm. - SpringerBriefs in computer science,2191-5768. - SpringerBriefs in computer science..

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.

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.

ISBN: 9783030543044$q(electronic bk.)

Standard No.: 10.1007/978-3-030-54304-4doiSubjects--Topical Terms:

190935
Time-series analysis
--Data processing.

LC Class. No.: QA280 / .R93 2020

Dewey Class. No.: 519.55

Universal time-series forecasting with mixture predictors
LDR:01725nmm a2200349 a 4500 001 585912
003 DE-He213
005 20200926173539.0
006 m d
007 cr nn 008maaau
008 210323s2020 sz s 0 eng d
020 $a 9783030543044$q(electronic bk.)
020 $a 9783030543037$q(paper)
024 7 $a 10.1007/978-3-030-54304-4 $2 doi
035 $a 978-3-030-54304-4
040 $a GP $c GP
041 0 $a eng
050 4 $a QA280 $b .R93 2020
072 7 $a UY $2 bicssc
072 7 $a COM014000 $2 bisacsh
072 7 $a UY $2 thema
072 7 $a UYA $2 thema
082 0 4 $a 519.55 $2 23
090 $a QA280 $b .R988 2020
100 1 $a Ryabko, Daniil. $3 877176
245 1 0 $a Universal time-series forecasting with mixture predictors $h [electronic resource] / $c by Daniil Ryabko.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2020.
300 $a viii, 85 p. : $b ill., digital ; $c 24 cm.
490 1 $a SpringerBriefs in computer science, $x 2191-5768
505 0 $a 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.
520 $a 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.
650 0 $a Time-series analysis $x Data processing. $3 190935
650 1 4 $a Theory of Computation. $3 274475
650 2 4 $a Artificial Intelligence. $3 212515
650 2 4 $a Mathematics of Computing. $3 273710
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
830 0 $a SpringerBriefs in computer science. $3 559641
856 4 0 $u https://doi.org/10.1007/978-3-030-54304-4
950 $a Computer Science (SpringerNature-11645)