Concentration Inequalities: A Nonasymptotic Theory of Independence
| Author | : | |
| Rating | : | 4.64 (645 Votes) |
| Asin | : | 019876765X |
| Format Type | : | paperback |
| Number of Pages | : | 496 Pages |
| Publish Date | : | 2017-09-29 |
| Language | : | English |
DESCRIPTION:
Applications to the study of empirical processes, random projections, random matrix theory, and threshold phenomena are also presented.A self-contained introduction to concentration inequalities, it includes a survey of concentration of sums of independent random variables, variance bounds, the entropy method, and the transportation method. Roughly speaking, if a function of many independent random variables does not depend too much on any of the variables then it is concentrated in the sense that with high probability, it is close to its expected value. Deep connections with isoperimetric problems are revealed whilst special attention is paid to applications to the supremum of empirical processes. Written by leading experts in the field and containing extensive exercise sections this book will be an invaluable resourc
"The clear exposition from basic material up to recent sophisticated results and lucid writing style make the text a pleasure to read. Beginners as well as experienced scientists will prot equally from it. It will certainly become one of the standard references in the field." --Hilmar Mai, Zentralblatt Math
"Three Stars" according to Book_Reader. Dry math. Not to learn about the subject.. This is a truly wonderful book, that manages to convey the richness of This is a truly wonderful book, that manages to convey the richness of concentration inequalities while maintainingclarity and focus. Connections to entropy, influences, convex geometry and isoperimetric inequalities are highlighted.The book should be useful for novices as well as seasoned experts. A remarkable achievement.. This book is awesome. Should definitely be present in the bookshelf of Matey This book is awesome. Should definitely be present in the bookshelf of anyone who is working in stats/ML. Proofs are simple and succinct, and the material is presented in an extremely clear and well organized fashion. The authors are well known experts in the area. 5/5
. Stephane Boucheron, Laboratoire de Probabilites et Modeles Aleatoires, Universite Paris-Diderot,Gabor Lugosi, ICREA Research Professor, Pompeu Fabra University,Pascal Massart, Laboratoire de Mathematiques, Universite Paris Sud and Institut Universitaire de FranceStephane Boucheron is a Professor in the Applied Mathematics and Statistics Department at Universite Paris-Diderot, France. Gabor Lugosi is ICREA Research Professor in the Department