Model Selection for Regularized Least-Squares Algorithm in Learning Theory
نویسندگان
چکیده
منابع مشابه
Model Selection for Regularized Least-Squares Algorithm in Learning Theory
We investigate the problem of model selection for learning algorithms depending on a continuous parameter. We propose a model selection procedure based on a worst case analysis and data-independent choice of the parameter. For regularized least-squares algorithm we bound the generalization error of the solution by a quantity depending on few known constants and we show that the corresponding mo...
متن کاملRisk Bounds and Model Selection for Regularized Least Squares
Motivation: A central problem in learning theory is a quantitative assessment of the inference property of a learning algorithm ensuring consistency. A number of seminal works show that the essential feature of an algorithm should be its capacity of controlling the complexity of the solution, this is usually realized introducing a parametric family of learning algorithms in which the parameters...
متن کاملOptimal Rates for Regularized Least-squares Algorithm
We develop a theoretical analysis of the generalization performances of regularized least-squares algorithm on a reproducing kernel Hilbert space in the supervised learning setting. The presented results hold in the general framework of vector-valued functions, therefore they can be applied to multi-task problems. In particular we observe that the concept of effective dimension plays a central ...
متن کاملFast Rates for Regularized Least-squares Algorithm
We develop a theoretical analysis of generalization performances of regularized leastsquares on reproducing kernel Hilbert spaces for supervised learning. We show that the concept of effective dimension of an integral operator plays a central role in the definition of a criterion for the choice of the regularization parameter as a function of the number of samples. In fact a minimax analysis is...
متن کاملA Sparse Regularized Least-Squares Preference Learning Algorithm
Learning preferences between objects constitutes a challenging task that notably differs from standard classification or regression problems. The objective involves prediction of ordering of the data points. Furthermore, methods for learning preference relations usually are computationally more demanding than standard classification or regression methods. Recently, we have proposed a kernel bas...
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: Foundations of Computational Mathematics
سال: 2004
ISSN: 1615-3375,1615-3383
DOI: 10.1007/s10208-004-0134-1