國立虎尾科技大學 |

High-dimensional probability : = an introduction with applications in data science /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	High-dimensional probability :/ Roman Vershynin.
其他題名:	an introduction with applications in data science /
作者:	Vershynin, Roman,
面頁冊數:	1 online resource (xiv, 284 pages) :digital, PDF file(s). :
附註:	Title from publisher's bibliographic system (viewed on 28 Sep 2018).
標題:	Random variables. -
電子資源:	https://doi.org/10.1017/9781108231596
ISBN:	9781108231596 (ebook)

High-dimensional probability : = an introduction with applications in data science /
Vershynin, Roman,1974-

High-dimensional probability :an introduction with applications in data science /Roman Vershynin. - 1 online resource (xiv, 284 pages) :digital, PDF file(s). - Cambridge series in statistical and probabilistic mathematics ;47. - Cambridge series in statistical and probabilistic mathematics ;53..

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: 9781108231596 (ebook)Subjects--Topical Terms:

598296
Random variables.

LC Class. No.: QA273 / .V4485 2018

Dewey Class. No.: 519.2

High-dimensional probability : = an introduction with applications in data science /
LDR:02612nam a22003018i 4500 001 1124809
003 UkCbUP
005 20181002135011.0
006 m|||||o||d||||||||
007 cr||||||||||||
008 240926s2018||||enk o ||1 0|eng|d
020 $a 9781108231596 (ebook)
020 $z 9781108415194 (hardback)
035 $a CR9781108231596
040 $a UkCbUP $b eng $e rda $c UkCbUP
050 0 0 $a QA273 $b .V4485 2018
082 0 0 $a 519.2 $2 23
100 1 $a Vershynin, Roman, $d 1974- $e author. $3 1442590
245 1 0 $a High-dimensional probability : $b an introduction with applications in data science / $c Roman Vershynin.
264 1 $a Cambridge : $b Cambridge University Press, $c 2018.
300 $a 1 online resource (xiv, 284 pages) : $b digital, PDF file(s).
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
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 Random variables. $3 598296
650 0 $a Stochastic processes. $3 528256
650 0 $a Probabilities. $3 527847
776 0 8 $i Print version: $z 9781108415194
830 0 $a Cambridge series in statistical and probabilistic mathematics ; $v 53. $3 1405725
856 4 0 $u https://doi.org/10.1017/9781108231596