In the present paper, we give an investigation on the learning rate of l2-coefficient regularized classification with strong loss and the data dependent kernel functional spaces. The results show that the learning rate is influenced by the strong convexity.
In this paper, we shall study the solutions of functional equations of the formΦ=∑α∈Zsa（α）Φ（M.-α）where is an r × 1 column vector of functions on the s-dimensional Euclidean space,a ：= （a（a））α∈Zs is an exponentially decaying sequence of r × r complex matrices called refinement mask and M is an s × s integer matrix such that limn∞ M-n =0. We axe interested in the question, for a mask a with exponential decay, if there exists a solution ~ to the functional equation with each function φj, j = 1,... ,r, belonging to L2（Rs） and having exponential decay in some sense？ Our approach will be to consider the convergence of vector cascade algorithms in weighted L2 spaces. The vector cascade operator Qa,M associated with mask a and matrix M is defined by
The cascade algorithm plays an important role in computer graphics and wavelet analysis.In this paper,we first investigate the convergence of cascade algorithms associated with a polynomially decaying mask and a general dilation matrix in L p (R s) (1 p ∞) spaces,and then we give an error estimate of the cascade algorithms associated with truncated masks.It is proved that under some appropriate conditions if the cascade algorithm associated with a polynomially decaying mask converges in the L p-norm,then the cascade algorithms associated with the truncated masks also converge in the L p-norm.Moreover,the error between the two resulting limit functions is estimated in terms of the masks.
The dual-tree complex wavelet transform is a useful tool in signal and image process- ing. In this paper, we propose a dual-tree complex wavelet transform （CWT） based algorithm for image inpalnting problem. Our approach is based on Cai, Chan, Shen and Shen＇s framelet-based algorithm. The complex wavelet transform outperforms the standard real wavelet transform in the sense of shift-invariance, directionality and anti-aliasing. Numerical results illustrate the good performance of our algorithm.
