Weak approximation of an invariant measure and a low boundary of the entropy, II

Abstract

For a measurable map $T$ and a sequence of $T$-invariant probability measures $\mu_n$ that converges in some sense to a $T$-invariant probability measure $\mu$, an estimate from below for the Kolmogorov--Sinai entropy of $T$ with respect to $\mu$ is suggested in terms of the entropies of $T$ with respect to $\mu_1$, $\mu_2$, \dots. This result is obtained under the assumption that some generating partition has finite entropy. By an explicite example it is shown that, in general, this assumption cannot be removed.