Kernel Mean Estimation and Stein's Effect

نویسندگان

  • Krikamol Muandet
  • Kenji Fukumizu
  • Bharath K. Sriperumbudur
  • Arthur Gretton
  • Bernhard Schölkopf
چکیده

A mean function in reproducing kernel Hilbert space, or a kernel mean, is an important part of many applications ranging from kernel principal component analysis to Hilbert-space embedding of distributions. Given finite samples, an empirical average is the standard estimate for the true kernel mean. We show that this estimator can be improved via a well-known phenomenon in statistics called Stein’s phenomenon. After consideration, our theoretical analysis reveals the existence of a wide class of estimators that are better than the standard. Focusing on a subset of this class, we propose efficient shrinkage estimators for the kernel mean. Empirical evaluations on several benchmark applications clearly demonstrate that the proposed estimators outperform the standard kernel mean estimator. Date: May 7, 2014. 1 2 KERNEL MEAN ESTIMATION AND STEIN’S EFFECT

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

Comments on Multiparameter Estimation in Truncated Power Series Distributions under the Stein's Loss

This comment is to show that Theorem3.3 of Dey and Chung (1991) (Multiparameter estimation intruncated power series distributions under the Stein's loss.emph{Commun. Statist.-Theory Meth.,} {bf 20}, 309-326) may giveus misleading results. Analytically and through simulation, weshow that the Theorem does not improve the given estimator.

متن کامل

THE COMPARISON OF TWO METHOD NONPARAMETRIC APPROACH ON SMALL AREA ESTIMATION (CASE: APPROACH WITH KERNEL METHODS AND LOCAL POLYNOMIAL REGRESSION)

Small Area estimation is a technique used to estimate parameters of subpopulations with small sample sizes.  Small area estimation is needed  in obtaining information on a small area, such as sub-district or village.  Generally, in some cases, small area estimation uses parametric modeling.  But in fact, a lot of models have no linear relationship between the small area average and the covariat...

متن کامل

Nonparametric Regression Estimation under Kernel Polynomial Model for Unstructured Data

The nonparametric estimation(NE) of kernel polynomial regression (KPR) model is a powerful tool to visually depict the effect of covariates on response variable, when there exist unstructured and heterogeneous data. In this paper we introduce KPR model that is the mixture of nonparametric regression models with bootstrap algorithm, which is considered in a heterogeneous and unstructured framewo...

متن کامل

The Relative Improvement of Bias Reduction in Density Estimator Using Geometric Extrapolated Kernel

One of a nonparametric procedures used to estimate densities is kernel method. In this paper, in order to reduce bias of  kernel density estimation, methods such as usual kernel(UK), geometric extrapolation usual kernel(GEUK), a bias reduction kernel(BRK) and a geometric extrapolation bias reduction kernel(GEBRK) are introduced. Theoretical properties, including the selection of smoothness para...

متن کامل

Error estimation for nonlinear pseudoparabolic equations with nonlocal boundary conditions in reproducing kernel space

In this paper we discuss about nonlinear pseudoparabolic equations with nonlocal boundary conditions and their results. An effective error estimation for this method altough has not yet been discussed. The aim of this paper is to fill this gap.

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:
  • CoRR

دوره abs/1306.0842  شماره 

صفحات  -

تاریخ انتشار 2013