A Bennett Concentration Inequality and Its Application to Suprema of Empirical Processes

نویسندگان

  • Olivier BOUSQUET
  • O. Bousquet
چکیده

We introduce new concentration inequalities for functions on product spaces They allow to obtain a Bennett type deviation bound for suprema of empirical processes indexed by upper bounded functions. The result is an improvement on Rio’s version [6] of Talagrand’s inequality [7] for equidistributed variables. c 2001 Académie des sciences/Éditions scientifiques et médicales Elsevier SAS Une inégalité de concentration de type Bennett et son application aux maxima de processus empiriques Résumé. Nous proposons deux inégalités de concentration pour des fonctions de n variables indépendantes. L’une d’elles permet d’obtenir une inégalité de déviation de type Bennett pour les processus empiriques indexés par des classes de fonctions bornées à droite. Cela améliore la version donnée par Rio [6] de l’inégalité de Talagrand [7] pour des observations équidistribuées. c 2001 Académie des sciences/Éditions scientifiques et médicales Elsevier SAS Version française abrégée

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Compensator and exponential inequalities for some suprema of counting processes

Talagrand [1996. New concentration inequalities in product spaces. Invent. Math. 126 (3), 505–563], Ledoux [1996. On Talagrand deviation inequalities for product measures. ESAIM: Probab. Statist. 1, 63–87], Massart [2000a. About the constants in Talagrand’s concentration inequalities for empirical processes. Ann. Probab. 2 (28), 863–884], Rio [2002. Une inégalité de Bennett pour les maxima de p...

متن کامل

Ratio Limit Theorems for Empirical Processes

Concentration inequalities are used to derive some new inequalities for ratio-type suprema of empirical processes. These general inequalities are used to prove several new limit theorems for ratio-type suprema and to recover a number of the results from [1] and [2]. As a statistical application, an oracle inequality for nonparametric regression is obtained via ratio bounds.

متن کامل

An Inequality with Applications to Structured Sparsity and Multitask Dictionary Learning

From concentration inequalities for the suprema of Gaussian or Rademacher processes an inequality is derived. It is applied to sharpen existing and to derive novel bounds on the empirical Rademacher complexities of unit balls in various norms appearing in the context of structured sparsity and multitask dictionary learning or matrix factorization. A key role is played by the largest eigenvalue ...

متن کامل

On Gaussian comparison inequality and its application to spectral analysis of large random matrices

Recently, Chernozhukov, Chetverikov, and Kato [Ann. Statist. 42 (2014) 1564–1597] developed a new Gaussian comparison inequality for approximating the suprema of empirical processes. This paper exploits this technique to devise sharp inference on spectra of large random matrices. In particular, we show that two long-standing problems in random matrix theory can be solved: (i) simple bootstrap i...

متن کامل

A Bernstein-type Inequality for Suprema of Random Processes with an Application to Statistics

We use the generic chaining device proposed by Talagrand to establish exponential bounds on the deviation probability of some suprema of random processes. Then, given a random vector ξ in R the components of which are independent and admit a suitable exponential moment, we deduce a deviation inequality for the squared Euclidean norm of the projection of ξ onto a linear subspace of R. Finally, w...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2002