大葉大學圖書館 |

High-dimensional probability[electronic resource] :an introduction with applications in data science /

纪录类型:	书目-电子资源 : Monograph/item
[NT 15000414] null:	519.2
[NT 47271] Title/Author:	High-dimensional probability : an introduction with applications in data science // Roman Vershynin.
作者:	Vershynin, Roman.
出版者:	Cambridge : : Cambridge University Press,, 2018.
面页册数:	xiv, 284 p. : : ill., digital ;; 24 cm.
附注:	Title from publisher's bibliographic system (viewed on 28 Sep 2018).
标题:	Probabilities.
标题:	Stochastic processes.
标题:	Random variables.
ISBN:	9781108231596
ISBN:	9781108415194
[NT 15000228] null:	Preliminaries on random variables -- Concentration of sums of independent random variables -- Random vectors in high dimensions -- Random matrices -- Concentration without independence -- Quadratic forms, symmetrization and contraction -- Random processes -- Chaining -- Deviations of random matrices and geometric consequences -- Sparse recovery -- Dvoretzky-Milman's theorem.
[NT 15000229] null:	High-dimensional probability offers insight into the behavior of random vectors, random matrices, random subspaces, and objects used to quantify uncertainty in high dimensions. Drawing on ideas from probability, analysis, and geometry, it lends itself to applications in mathematics, statistics, theoretical computer science, signal processing, optimization, and more. It is the first to integrate theory, key tools, and modern applications of high-dimensional probability. Concentration inequalities form the core, and it covers both classical results such as Hoeffding's and Chernoff's inequalities and modern developments such as the matrix Bernstein's inequality. It then introduces the powerful methods based on stochastic processes, including such tools as Slepian's, Sudakov's, and Dudley's inequalities, as well as generic chaining and bounds based on VC dimension. A broad range of illustrations is embedded throughout, including classical and modern results for covariance estimation, clustering, networks, semidefinite programming, coding, dimension reduction, matrix completion, machine learning, compressed sensing, and sparse regression.
电子资源:	https://doi.org/10.1017/9781108231596

High-dimensional probability[electronic resource] :an introduction with applications in data science /
Vershynin, Roman.

High-dimensional probabilityan introduction with applications in data science /[electronic resource] :Roman Vershynin. - Cambridge :Cambridge University Press,2018. - xiv, 284 p. :ill., digital ;24 cm. - Cambridge series in statistical and probabilistic mathematics ;47. - Cambridge series in statistical and probabilistic mathematics ;47..

Title from publisher's bibliographic system (viewed on 28 Sep 2018).

Preliminaries on random variables -- Concentration of sums of independent random variables -- Random vectors in high dimensions -- Random matrices -- Concentration without independence -- Quadratic forms, symmetrization and contraction -- Random processes -- Chaining -- Deviations of random matrices and geometric consequences -- Sparse recovery -- Dvoretzky-Milman's theorem.

High-dimensional probability offers insight into the behavior of random vectors, random matrices, random subspaces, and objects used to quantify uncertainty in high dimensions. Drawing on ideas from probability, analysis, and geometry, it lends itself to applications in mathematics, statistics, theoretical computer science, signal processing, optimization, and more. It is the first to integrate theory, key tools, and modern applications of high-dimensional probability. Concentration inequalities form the core, and it covers both classical results such as Hoeffding's and Chernoff's inequalities and modern developments such as the matrix Bernstein's inequality. It then introduces the powerful methods based on stochastic processes, including such tools as Slepian's, Sudakov's, and Dudley's inequalities, as well as generic chaining and bounds based on VC dimension. A broad range of illustrations is embedded throughout, including classical and modern results for covariance estimation, clustering, networks, semidefinite programming, coding, dimension reduction, matrix completion, machine learning, compressed sensing, and sparse regression.

ISBN: 9781108231596Subjects--Topical Terms:

171876
Probabilities.

LC Class. No.: QA273 / .V4485 2018

Dewey Class. No.: 519.2

High-dimensional probability[electronic resource] :an introduction with applications in data science /
LDR:02458nmm a2200265 a 4500 001 539338
003 UkCbUP
005 20181002135011.0
006 m d
007 cr nn 008maaau
008 231121s2018 enk o 1 0 eng d
020 $a 9781108231596 $q (electronic bk.)
020 $a 9781108415194 $q (hardback)
035 $a CR9781108231596
040 $a UkCbUP $b eng $c UkCbUP $d GP
050 0 0 $a QA273 $b .V4485 2018
082 0 0 $a 519.2 $2 23
090 $a QA273 $b .V563 2018
100 1 $a Vershynin, Roman. $3 767894
245 1 0 $a High-dimensional probability $h [electronic resource] : $b an introduction with applications in data science / $c Roman Vershynin.
260 $a Cambridge : $b Cambridge University Press, $c 2018.
300 $a xiv, 284 p. : $b ill., digital ; $c 24 cm.
490 1 $a Cambridge series in statistical and probabilistic mathematics ; $v 47
500 $a Title from publisher's bibliographic system (viewed on 28 Sep 2018).
505 0 $a Preliminaries on random variables -- Concentration of sums of independent random variables -- Random vectors in high dimensions -- Random matrices -- Concentration without independence -- Quadratic forms, symmetrization and contraction -- Random processes -- Chaining -- Deviations of random matrices and geometric consequences -- Sparse recovery -- Dvoretzky-Milman's theorem.
520 $a High-dimensional probability offers insight into the behavior of random vectors, random matrices, random subspaces, and objects used to quantify uncertainty in high dimensions. Drawing on ideas from probability, analysis, and geometry, it lends itself to applications in mathematics, statistics, theoretical computer science, signal processing, optimization, and more. It is the first to integrate theory, key tools, and modern applications of high-dimensional probability. Concentration inequalities form the core, and it covers both classical results such as Hoeffding's and Chernoff's inequalities and modern developments such as the matrix Bernstein's inequality. It then introduces the powerful methods based on stochastic processes, including such tools as Slepian's, Sudakov's, and Dudley's inequalities, as well as generic chaining and bounds based on VC dimension. A broad range of illustrations is embedded throughout, including classical and modern results for covariance estimation, clustering, networks, semidefinite programming, coding, dimension reduction, matrix completion, machine learning, compressed sensing, and sparse regression.
650 0 $a Probabilities. $3 171876
650 0 $a Stochastic processes. $3 177592
650 0 $a Random variables. $3 467606
830 0 $a Cambridge series in statistical and probabilistic mathematics ; $v 47. $3 767895
856 4 0 $u https://doi.org/10.1017/9781108231596