| J. Krob and H.v. Weizsacker. The rate of information gain in experiments with a finite parameter set. submitted, 1993. |
....transition matrix belongs to a known finite set. In the case of iid. sequences and two parameters this question was in a certain sense answered by Chernoff [Che52] Later Torgersen (e.g. Tor81] extended Chernoff s Theorem to a finite parameter set using the frame of abstract decision theory. In [KW93] it was shown that in finite parameter problems generally the decision theoretic rate and the Shannon theoretic rate coincide, where the former is measured by the minimal Bayes risk or equivalently by the deficiency distance to the most informative experiment and the latter is the rate of the ....
....be denoted by the letter V; i.e. V ffi (Q) fP 2 M : jP i;j Gamma Q i;j j ffi for all i; jg. Further we set V ffi (Q) V ffi (Q) M : So U ffi (Q) V Q ffi (Q) 3 The risk rates The following result is the starting point of this paper. It is a special case of the main result of [KW93]. Proposition 1: Let ff = ff 1 ; ff l ) be any strictly positive prior. Suppose that for every 2 Theta = f1; lg the process (X i ) i2IN 0 forms under P a Markov chain with the irreducible transition matrix where 7 is injective. Then a) lim n 1 B n (ffjX) lim ....
[Article contains additional citation context not shown here]
J. Krob and H.v. Weizsacker. The rate of information gain in experiments with a finite parameter set. submitted, 1993.
No context found.
J. Krob and H.v. Weizsacker. The rate of information gain in experiments with a finite parameter set. submitted, 1993.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC