國立虎尾科技大學 |

Algorithmic learning in a random world

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Algorithmic learning in a random world/ by Vladimir Vovk, Alexander Gammerman, Glenn Shafer.
Author:	Vovk, Vladimir.
other author:	Gammerman, A.
Published:	Cham :Springer International Publishing : : 2022.,
Description:	xxvi, 476 p. :ill., digital ; : 24 cm.;
Contained By:	Springer Nature eBook
Subject:	Prediction theory. -
Online resource:	https://doi.org/10.1007/978-3-031-06649-8
ISBN:	9783031066498

Algorithmic learning in a random world
Vovk, Vladimir.

Algorithmic learning in a random world[electronic resource] /by Vladimir Vovk, Alexander Gammerman, Glenn Shafer. - Second edition. - Cham :Springer International Publishing :2022. - xxvi, 476 p. :ill., digital ;24 cm.

1. Introduction -- Part I Set prediction -- 2. Conformal prediction: general case and regression -- 3. Conformal prediction: classification and general case -- 4. Modifications of conformal predictors -- Part II Probabilistic prediction -- 5. Impossibility results -- 6. Probabilistic classification: Venn predictors -- 7. Probabilistic regression: conformal predictive systems -- Part III Testing randomness -- 8. Testing exchangeability -- 9. Efficiency of conformal testing -- 10. Non-conformal shortcut -- Part IV Online compression modelling -- 11. Generalized conformal prediction -- 12. Generalized Venn prediction and hypergraphical models -- 13. Contrasts and perspectives.

This book is about conformal prediction, an approach to prediction that originated in machine learning in the late 1990s. The main feature of conformal prediction is the principled treatment of the reliability of predictions. The prediction algorithms described - conformal predictors - are provably valid in the sense that they evaluate the reliability of their own predictions in a way that is neither over-pessimistic nor over-optimistic (the latter being especially dangerous) The approach is still flexible enough to incorporate most of the existing powerful methods of machine learning. The book covers both key conformal predictors and the mathematical analysis of their properties. Algorithmic Learning in a Random World contains, in addition to proofs of validity, results about the efficiency of conformal predictors. The only assumption required for validity is that of "randomness" (the prediction algorithm is presented with independent and identically distributed examples); in later chapters, even the assumption of randomness is significantly relaxed. Interesting results about efficiency are established both under randomness and under stronger assumptions. Since publication of the First Edition in 2005 conformal prediction has found numerous applications in medicine and industry, and is becoming a popular machine-learning technique. This Second Edition contains three new chapters. One is about conformal predictive distributions, which are more informative than the set predictions produced by standard conformal predictors. Another is about the efficiency of ways of testing the assumption of randomness based on conformal prediction. The third new chapter harnesses conformal testing procedures for protecting machine-learning algorithms against changes in the distribution of the data. In addition, the existing chapters have been revised, updated, and expanded.

ISBN: 9783031066498

Standard No.: 10.1007/978-3-031-06649-8doiSubjects--Topical Terms:

569153
Prediction theory.

LC Class. No.: QA279.2

Dewey Class. No.: 519.287

Algorithmic learning in a random world
LDR:03596nam a2200337 a 4500 001 1097923
003 DE-He213
005 20221213193653.0
006 m d
007 cr nn 008maaau
008 230419s2022 sz s 0 eng d
020 $a 9783031066498 $q (electronic bk.)
020 $a 9783031066481 $q (paper)
024 7 $a 10.1007/978-3-031-06649-8 $2 doi
035 $a 978-3-031-06649-8
040 $a GP $c GP
041 0 $a eng
050 4 $a QA279.2
072 7 $a UYQM $2 bicssc
072 7 $a COM004000 $2 bisacsh
072 7 $a UYQM $2 thema
082 0 4 $a 519.287 $2 23
090 $a QA279.2 $b .V973 2022
100 1 $a Vovk, Vladimir. $3 669774
245 1 0 $a Algorithmic learning in a random world $h [electronic resource] / $c by Vladimir Vovk, Alexander Gammerman, Glenn Shafer.
250 $a Second edition.
260 $a Cham : $c 2022. $b Springer International Publishing : $b Imprint: Springer,
300 $a xxvi, 476 p. : $b ill., digital ; $c 24 cm.
505 0 $a 1. Introduction -- Part I Set prediction -- 2. Conformal prediction: general case and regression -- 3. Conformal prediction: classification and general case -- 4. Modifications of conformal predictors -- Part II Probabilistic prediction -- 5. Impossibility results -- 6. Probabilistic classification: Venn predictors -- 7. Probabilistic regression: conformal predictive systems -- Part III Testing randomness -- 8. Testing exchangeability -- 9. Efficiency of conformal testing -- 10. Non-conformal shortcut -- Part IV Online compression modelling -- 11. Generalized conformal prediction -- 12. Generalized Venn prediction and hypergraphical models -- 13. Contrasts and perspectives.
520 $a This book is about conformal prediction, an approach to prediction that originated in machine learning in the late 1990s. The main feature of conformal prediction is the principled treatment of the reliability of predictions. The prediction algorithms described - conformal predictors - are provably valid in the sense that they evaluate the reliability of their own predictions in a way that is neither over-pessimistic nor over-optimistic (the latter being especially dangerous) The approach is still flexible enough to incorporate most of the existing powerful methods of machine learning. The book covers both key conformal predictors and the mathematical analysis of their properties. Algorithmic Learning in a Random World contains, in addition to proofs of validity, results about the efficiency of conformal predictors. The only assumption required for validity is that of "randomness" (the prediction algorithm is presented with independent and identically distributed examples); in later chapters, even the assumption of randomness is significantly relaxed. Interesting results about efficiency are established both under randomness and under stronger assumptions. Since publication of the First Edition in 2005 conformal prediction has found numerous applications in medicine and industry, and is becoming a popular machine-learning technique. This Second Edition contains three new chapters. One is about conformal predictive distributions, which are more informative than the set predictions produced by standard conformal predictors. Another is about the efficiency of ways of testing the assumption of randomness based on conformal prediction. The third new chapter harnesses conformal testing procedures for protecting machine-learning algorithms against changes in the distribution of the data. In addition, the existing chapters have been revised, updated, and expanded.
650 0 $a Prediction theory. $3 569153
650 0 $a Algorithms. $3 527865
650 0 $a Stochastic processes. $3 528256
700 1 $a Gammerman, A. $3 1408222
700 1 $a Shafer, Glenn. $3 528124
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
856 4 0 $u https://doi.org/10.1007/978-3-031-06649-8
950 $a Mathematics and Statistics (SpringerNature-11649)