Regularized Least Square Regression with Unbounded and Dependent Sampling
نویسندگان
چکیده
منابع مشابه
Regularized Least Square Regression with Unbounded and Dependent Sampling
and Applied Analysis 3 Theorem 4. Suppose that the unbounded hypothesis with p > 2 holds, L−r K f ρ ∈ L 2 ρX (X) for some r > 0, and theα-mixing coefficients satisfy a polynomial decay, that is, α l ≤ bl −t for some b > 0 and t > 0. Then, for any 0 < η < 1, one has with confidence 1 − η, fz,γ − ρ ρX = O(m −θmin{(p−2)t/p,1} (logm)1/2) , (13) where θ is given by θ = { { { { { {...
متن کاملLearning Rates of Least-Square Regularized Regression
This paper considers the regularized learning algorithm associated with the leastsquare loss and reproducing kernel Hilbert spaces. The target is the error analysis for the regression problem in learning theory. A novel regularization approach is presented, which yields satisfactory learning rates. The rates depend on the approximation property and the capacity of the reproducing kernel Hilbert...
متن کاملError analysis of regularized least-square regression with Fredholm kernel
Learning with Fredholm kernel has attracted increasing attention recently since it can effectively utilize the data information to improve the prediction performance. Despite rapid progress on theoretical and experimental evaluations, its generalization analysis has not been explored in learning theory literature. In this paper, we establish the generalization bound of least square regularized ...
متن کاملRegularized Least Square Regression with Spherical Polynomial Kernels
This article considers regularized least square regression on the sphere. It develops a theoretical analysis of the generalization performances of regularized least square regression algorithm with spherical polynomial kernels. The explicit bounds are derived for the excess risk error. The learning rates depend on the eigenvalues of spherical polynomial integral operators and on the dimension o...
متن کاملRegularized Latent Least Square Regression for Cross Pose Face Recognition
Pose variation is one of the challenging factors for face recognition. In this paper, we propose a novel cross-pose face recognition method named as Regularized Latent Least Square Regression (RLLSR). The basic assumption is that the images captured under different poses of one person can be viewed as pose-specific transforms of a single ideal object. We treat the observed images as regressor, ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Abstract and Applied Analysis
سال: 2013
ISSN: 1085-3375,1687-0409
DOI: 10.1155/2013/139318