User:IssaRice/Logical inductor construction: Difference between revisions
No edit summary |
No edit summary |
||
Line 1: | Line 1: | ||
==Lemma 5.1.1 (Fixed Point Lemma)== | |||
The following is used in the Fixed Point Lemma (5.1.1): | |||
Writing the <math>n</math>-strategy as | |||
:<math>T_n = \sum_{j=1}^k \xi_j \phi_j - \sum_{j=1}^k \xi_j\phi_j^{*n}</math> | |||
we have | |||
:<math>\mathbb V(T_n(\mathbb P_{\leq n-1}, \mathbb V)) = \sum_{j=1}^k \xi_j(\mathbb P_{\leq n-1}, \mathbb V)\cdot \mathbb V(\phi_j) - \sum_{j=1}^k \xi_j(\mathbb P_{\leq n-1}, \mathbb V) \cdot \phi_j^{*n}(\mathbb P_{\leq n-1}, \mathbb V)</math> | |||
But <math>\phi_j^{*n}(\mathbb P_{\leq n-1}, \mathbb V) = \mathbb V(\phi_j)</math> so the two sums cancel to obtain <math>0</math>. | |||
==See also== | ==See also== | ||
* https://machinelearning.subwiki.org/wiki/User:IssaRice/Logical_induction_notation | * https://machinelearning.subwiki.org/wiki/User:IssaRice/Logical_induction_notation |
Revision as of 00:50, 25 June 2019
Lemma 5.1.1 (Fixed Point Lemma)
The following is used in the Fixed Point Lemma (5.1.1):
Writing the -strategy as
we have
But so the two sums cancel to obtain .