Comments on "Weaker conditions for innovations informational equivalence in the independent Gaussian case"
暂无分享,去创建一个
The purpose of this correspondence is to point out a "noncausal" property of reproducing kernel Hilbert spaces which vitiates much of the argument of the above paper. It is, however, argued that the results claimed in the paper are nevertheless substantially correct.
[1] M. H. A. Davis,et al. A direct proof of innovations/observations equivalence for Gaussian procedures (Corresp.) , 1978, IEEE Trans. Inf. Theory.