SKOLKOVO School of Management

Bühlmann, Peter.

Statistics for high-dimensional data : methods, theory and applications / Peter Bühlmann, Sara van de Geer. - Heidelberg ; New York : Springer, c2011. - xvii, 556 p. : ill. (some col.) ; 24 cm. - Springer series in statistics . - Springer series in statistics. .

Includes bibliographical references (p. 547-556) and indexes.

Introduction -- Lasso for linear models -- Generalized linear models and the Lasso -- The group Lasso --Additive models and many smooth univariate functions -- Theory for the Lasso -- Variable selection with the Lasso -- Theory for l₁/l₂-penalty procedures -- Non-convex loss functions and l₁-regulation -- Stable solutions -- P-values for linear models and beyond -- Boosting and greedy algorithms -- Graphical modeling -- Probabililty and moment inequalities.

9783642201912 (hdbk. : acidfree paper) 3642201911 (hdbk. : acidfree paper)

2011930793


Mathematical statistics.
Smoothness of functions.
Nonconvex programming.
Least absolute deviations (Statistics)
Linear models (Statistics)

QA276 / .B84 2011