Nonlinear approximation using Gaussian kernels
نویسندگان
چکیده
منابع مشابه
Nonlinear Approximation Using Gaussian Kernels
It is well-known that non-linear approximation has an advantage over linear schemes in the sense that it provides comparable approximation rates to those of the linear schemes, but to a larger class of approximands. This was established for spline approximations and for wavelet approximations, and more recently for homogeneous radial basis function (surface spline) approximations. However, no s...
متن کاملGeodesic Gaussian kernels for value function approximation
The least-squares policy iteration approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular and useful choice as a basis function. However, it does not allow for discontinuity which typically arises in real-world reinforcement learning tasks. In this paper, we propose a new basis function based on ...
متن کاملAverage Case Approximation: Convergence and Tractability of Gaussian Kernels
We study the problem of approximating functions of d variables in the average case setting for a separable Banach space Fd equipped with a zero-mean Gaussian measure. The covariance kernel of this Gaussian measure takes the form of a Gaussian that depends on shape parameters γl. We stress that d can be arbitrarily large. Our approximation error is defined in the L2 norm, and we study the minima...
متن کاملEvent Selection Using Adaptive Gaussian Kernels
The Probability Density Estimation method is a technique that uses Kernel Density Estimation techniques to derive a discriminate function which an be used for event selection. This approach has the advantage of handling complex dependencies in data without using the ‘black box’ approach of neural networks. We present a new variant of the Probability Density Estimation method that allows the use...
متن کاملLearning Kernels over Strings using Gaussian Processes
Non-contiguous word sequences are widely known to be important in modelling natural language. However they are not explicitly encoded in common text representations. In this work we propose a model for text processing using string kernels, capable of flexibly representing non-contiguous sequences. Specifically, we derive a vectorised version of the string kernel algorithm and their gradients, a...
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: Journal of Functional Analysis
سال: 2010
ISSN: 0022-1236
DOI: 10.1016/j.jfa.2010.02.001