Generalization bounds for function approximation from scattered noisy data

نویسندگان

  • Partha Niyogi
  • Federico Girosi
چکیده

We consider the problem of approximating functions from scattered data using linear superpositions of non-linearly parameterized functions. We show how the total error (generalization error) can be decomposed into two parts: an approximation part that is due to the finite number of parameters of the approximation scheme used; and an estimation part that is due to the finite number of data available. We bound each of these two parts under certain assumptions and prove a general bound for a class of approximation schemes that include radial basis functions and multilayer perceptrons.

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

Monotonicity Preserving Approximation of Multivariate Scattered Data ∗

This paper describes a new method of monotone interpolation and smoothing of multivariate scattered data. It is based on the assumption that the function to be approximated is Lipschitz continuous. The method provides the optimal approximation in the worst case scenario and tight error bounds. Smoothing of noisy data subject to monotonicity constraints is converted into a quadratic programming ...

متن کامل

Learning a function from noisy samples at a finite sparse set of points

In learning theory the goal is to reconstruct a function defined on some (typically high-dimensional) domain Ω, when only noisy values of this function at a sparse, discrete subset ω ⊂ Ω are available. In this work we use Koksma-Hlawka type estimates to obtain deterministic bounds on the so-called generalization error. The resulting estimates show, that the generalization error tends to zero, w...

متن کامل

Generalization Error Bounds for Noisy, Iterative Algorithms

In statistical learning theory, generalization error is used to quantify the degree to which a supervised machine learning algorithm may overfit to training data. Recent work [Xu and Raginsky (2017)] has established a bound on the generalization error of empirical risk minimization based on the mutual information I(S;W ) between the algorithm input S and the algorithm output W , when the loss f...

متن کامل

Reconstruction of Numerical Derivatives from Scattered Noisy Data

Based on the thin plate spline approximation theory, we propose in this paper an efficient regularization algorithm for the reconstruction of numerical derivatives from two-dimensional scattered noisy data. An error estimation that deduces a good regularization parameter is given. Numerical results show that the proposed method is efficient and stable.

متن کامل

Scattered data approximation of fully fuzzy data by quasi-interpolation

Fuzzy quasi-interpolations help to reduce the complexity of solving a linear system of equations compared with fuzzy interpolations. Almost all fuzzy quasi-interpolations are focused on the form of $widetilde{f}^{*}:mathbb{R}rightarrow F(mathbb{R})$ or $widetilde{f}^{*}:F(mathbb{R})rightarrow mathbb{R}$.  In this paper, we intend to offer a novel fuzzy radial basis function by the concept of so...

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:
  • Adv. Comput. Math.

دوره 10  شماره 

صفحات  -

تاریخ انتشار 1999