!()+,-./01 23456 (original) (raw)

Abstract

this report we describe how the Support Vector (SV) technique of solving linearoperator equations can be applied to the problem of density estimation [4]. Wepresent a new optimization procedure and set of kernels closely related to current SVtechniques that guarantee the monotonicity of the approximation. This techniqueestimates densities with a mixture of bumps (Gaussian-like shapes), with the usualSV property that only some coefficients are non-zero. Both the width and theheight of each bump is chosen adaptively ...

V. Vovk hasn't uploaded this paper.

Let V. know you want this paper to be uploaded.

Ask for this paper to be uploaded.