Vershynin, Roman. () High-dimensional probability :an introduction with applications in data scienceMLA Citation
Vershynin, Roman. High-dimensional Probability: An Introduction With Applications In Data Science. : . Print.
These citations may not conform precisely to your selected citation style. Please use this display as a guideline and modify as needed.
High-dimensional probability : an introduction with applications in data science /
Roman Vershynin, University of Michigan.
|Published:||Cambridge : Cambridge University Press, 2018.|
Cambridge series on statistical and probabilistic mathematics ; 47.
|Topics:||Probabilities. | Stochastic processes. | Random variables.|
|Author:||Vershynin, Roman, 1974-|
|Physical Description:||1 online resource.
|Includes:||Includes bibliographical references and index.
|ISBN:||9781108231596 (electronic bk.)
1108231594 (electronic bk.)
|Summary:||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.