High-Dimensional Probability 在线电子书 图书标签: 数学 Statistics 统计学 概率论 Machine_Learning DataScience 统计 statistics
发表于2024-11-22
High-Dimensional Probability 在线电子书 pdf 下载 txt下载 epub 下载 mobi 下载 2024
写得很棒!
评分写得很棒!
评分这个写得浅显易懂, 为了让更多做应用的人读懂吧. 第1-6章写得很好, 后面就有点意犹未尽草草收尾(特别是第11章). 其实应该多写一点几何泛函分析的, 比如john's ellipsoid什么的. Roman Vershynin其实是从几何泛函分析(他的专长)看这些问题, 与之对应的是van handel的notes, 就更加是从概率论的概率论看这些问题(所以有更多的篇幅讨论更精细的lower bound, 还有hypercontractivity这样的内容). 但是几何泛函分析一般不看hypercontractivity(毕竟主要是boolean cube上的), 即便是ledoux和talagrand的书也不提这个.
评分这个写得浅显易懂, 为了让更多做应用的人读懂吧. 第1-6章写得很好, 后面就有点意犹未尽草草收尾(特别是第11章). 其实应该多写一点几何泛函分析的, 比如john's ellipsoid什么的. Roman Vershynin其实是从几何泛函分析(他的专长)看这些问题, 与之对应的是van handel的notes, 就更加是从概率论的概率论看这些问题(所以有更多的篇幅讨论更精细的lower bound, 还有hypercontractivity这样的内容). 但是几何泛函分析一般不看hypercontractivity(毕竟主要是boolean cube上的), 即便是ledoux和talagrand的书也不提这个.
评分写得很棒!
Roman Vershynin is Professor of Mathematics at the University of California, Irvine. He studies random geometric structures across mathematics and data sciences, in particular in random matrix theory, geometric functional analysis, convex and discrete geometry, geometric combinatorics, high-dimensional statistics, information theory, machine learning, signal processing, and numerical analysis. His honors include an Alfred Sloan Research Fellowship in 2005, an invited talk at the International Congress of Mathematicians in Hyderabad in 2010, and a Bessel Research Award from the Humboldt Foundation in 2013. His 'Introduction to the Non-Asymptotic Analysis of Random Matrices' has become a popular educational resource for many new researchers in probability and data science.
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.
这个书居然作者不给errata也是很不user-friendly了. 根据已经出版的版本, 发现的数学错误或typo错误如下: p58, Exercise 3.5.3: 命题不总成立. 可补充条件"A对角线为0或A是PSD". Online version该处已修正. p83, Exercise 4.3.7(b): t log_2 (e/t) 疑应为 t log_2 (1/t). p96, ...
评分这个书居然作者不给errata也是很不user-friendly了. 根据已经出版的版本, 发现的数学错误或typo错误如下: p58, Exercise 3.5.3: 命题不总成立. 可补充条件"A对角线为0或A是PSD". Online version该处已修正. p83, Exercise 4.3.7(b): t log_2 (e/t) 疑应为 t log_2 (1/t). p96, ...
评分这个书居然作者不给errata也是很不user-friendly了. 根据已经出版的版本, 发现的数学错误或typo错误如下: p58, Exercise 3.5.3: 命题不总成立. 可补充条件"A对角线为0或A是PSD". Online version该处已修正. p83, Exercise 4.3.7(b): t log_2 (e/t) 疑应为 t log_2 (1/t). p96, ...
评分这个书居然作者不给errata也是很不user-friendly了. 根据已经出版的版本, 发现的数学错误或typo错误如下: p58, Exercise 3.5.3: 命题不总成立. 可补充条件"A对角线为0或A是PSD". Online version该处已修正. p83, Exercise 4.3.7(b): t log_2 (e/t) 疑应为 t log_2 (1/t). p96, ...
评分这个书居然作者不给errata也是很不user-friendly了. 根据已经出版的版本, 发现的数学错误或typo错误如下: p58, Exercise 3.5.3: 命题不总成立. 可补充条件"A对角线为0或A是PSD". Online version该处已修正. p83, Exercise 4.3.7(b): t log_2 (e/t) 疑应为 t log_2 (1/t). p96, ...
High-Dimensional Probability 在线电子书 pdf 下载 txt下载 epub 下载 mobi 下载 2024