Minimax Risk: Pinsker Bound

نویسنده

  • Michael Nussbaum
چکیده

We give an account of the Pinsker bound describing the exact asymptotics of the minimax risk in a class of nonparametric smoothing problems. The parameter spaces are Sobolev classes or ellipsoids, and the loss is of squared L2-type. The result from 1980 turned out to be a major step in the theory of nonparametric function estimation.

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

Minimax Bayes, asymptotic minimax and sparse wavelet priors

Pinsker(1980) gave a precise asymptotic evaluation of the minimax mean squared error of estimation of a signal in Gaussian noise when the signal is known a priori to lie in a compact ellipsoid in Hilbert space. This `Minimax Bayes' method can be applied to a variety of global non-parametric estimation settings with parameter spaces far from ellipsoidal. For example it leads to a theory of exact...

متن کامل

REACT Scatterplot Smoothers: Superefficiency through Basis Economy

REACT estimators for the mean of a linear model involve three steps: transforming the model to a canonical form that provides an economical representation of the unknown mean vector, estimating the risks of a class of candidate linear shrinkage estimators, and adaptively selecting the candidate estimator that minimizes estimated risk. Applied to oneor higherway layouts, the REACT method generat...

متن کامل

Quadratic functional estimation in inverse problems

We consider in this paper a Gaussian sequence model of observations Yi, i ≥ 1 having mean (or signal) θi and variance σi which is growing polynomially like i γ , γ > 0. This model describes a large panel of inverse problems. We estimate the quadratic functional of the unknown signal ∑ i≥1 θ 2 i when the signal belongs to ellipsoids of both finite smoothness functions (polynomial weights i, α > ...

متن کامل

Bounds on the Bayes and minimax risk for signal parameter estimation

A 3 r m h estimating the parameter 0 from a parametrized signal problem (with 0 5 0 5 L) observed through Gaussian white noise, four useful and computable lower bounds for the Bayes risk were developed. For problems with different L and Merent signal to noise ratios, some bounds am superior to the others. The lower bound obtained from taking the maximum of the four, serves not only as a good lo...

متن کامل

REACT Fits to Linear Models and Scatterplots

REACT estimators for the mean of a linear model involve three steps: transforming the model to a canonical form that provides an economical representation of the unknown mean vector, estimating the risks of a class of candidate linear shrinkage estimators, and adaptively selecting the candidate estimator that minimizes estimated risk. When the mean vector is smooth, the desired canonical form o...

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 2001