Empirical Bernstein Inequalities for U-Statistics

نویسندگان

  • Thomas Peel
  • Sandrine Anthoine
  • Liva Ralaivola
چکیده

We present original empirical Bernstein inequalities for U-statistics with bounded symmetric kernels q. They are expressed with respect to empirical estimates of either the variance of q or the conditional variance that appears in the Bernsteintype inequality for U-statistics derived by Arcones [2]. Our result subsumes other existing empirical Bernstein inequalities, as it reduces to them when U-statistics of order 1 are considered. In addition, it is based on a rather direct argument using two applications of the same (non-empirical) Bernstein inequality for U-statistics. We discuss potential applications of our new inequalities, especially in the realm of learning ranking/scoring functions. In the process, we exhibit an efficient procedure to compute the variance estimates for the special case of bipartite ranking that rests on a sorting argument. We also argue that our results may provide test set bounds and particularly interesting empirical racing algorithms for the problem of online learning of scoring functions.

برای دانلود 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

Moment Inequalities for Supremum of Empirical Processes of‎ ‎U-Statistic Structure and Application to Density Estimation

We derive moment inequalities for the supremum of empirical processes of U-Statistic structure and give application to kernel type density  estimation ‎and estimation of the distribution function for functions of observations.  

متن کامل

Exponential and Moment Inequalities for U-statistics

A Bernstein-type exponential inequality for (generalized) canonical U -statistics of order 2 is obtained and the Rosenthal and Hoffmann-Jørgensen inequalities for sums of independent random variables are extended to (generalized) U -statistics of any order whose kernels are either nonnegative or canonical.

متن کامل

On Bernstein Type Inequalities for Complex Polynomial

In this paper, we establish some Bernstein type inequalities for the complex polynomial. Our results constitute generalizations and refinements of some well-known polynomial inequalities.

متن کامل

Moderate Deviations for Functional U-processes

The moderate deviations principle is shown for the partial sums processes built on U-empirical measures of Polish space valued random variables and on U-statistics of real valued kernel functions. It is proved that in the non-degenerate case the conditions for the time xed principles suuce for the moderate deviations principle to carry over to the corresponding partial sums processes. Given a u...

متن کامل

Faster Hoeffding Racing: Bernstein Races via Jackknife Estimates

Hoeffding racing algorithms are used to achieve computational speedups in settings where the goal is to select a “best” option among a set of alternatives, but the amount of data is so massive that scoring all candidates using every data point is too costly. The key is to construct confidence intervals for scores of candidates that are used to eliminate options sequentially as more samples are ...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2010