Dynamics of continuous maps induced on the space of probability measures

TL;DR

This paper investigates the dynamical properties of induced maps on probability measure spaces, establishing conditions for transitivity, sensitivity, and chaos, and exploring differences between autonomous and non-autonomous systems.

Contribution

It provides sharp conditions linking the dynamics of a map and its induced map on probability measures, including transitivity, entropy, and chaos, with new results on non-autonomous systems.

Findings

Transitivity of (I,f) is equivalent to that of (M(I),f̂) under certain conditions.

Any transitive system (I,f) induces an infinite topological entropy on (M(I),f̂).

Li-Yorke and distributional chaos properties carry over from (X,f) to (M(X),f̂).

Abstract

For a continuous self-map $f$ on a compact interval $I$ and the induced map $\hat f$ on the space $\mathcal{M}(I)$ of probability measures, we obtain a sharp condition to guarantee that $(I,f)$ is transitive if and only if $(\mathcal{M}(I),\hat f)$ is transitive. We also show that the sensitivity of $(I,f)$ is equivalent to that of $(\mathcal{M}(I),\hat f)$. We prove that $(\mathcal{M}(I),\hat f)$ must have infinite topological entropy for any transitive system $(I,f)$, while there exists a transitive non-autonomous system $(I,f_{0,\infty})$ such that $(\mathcal{M}(I),\hat f_{0,\infty})$ has zero topological entropy, where $f_{0,\infty}=\{f_n\}_{n=0}^\infty$ is a sequence of continuous self-maps on $I$. For a continuous self-map $f$ on a general compact metric space $X$, we show that chain transitivity of $(X, f)$ implies chain mixing of $(\mathcal{M}(X),\hat f)$, and we provide two counterexamples to demonstrate that the converse is not true. We confirm that shadowing of $(X,f)$ is not inherited by $(\mathcal{M}(X),\hat f)$ in general. For a non-autonomous system $(X,f_{0,\infty})$, we prove that if $(\mathcal{M}(X),\hat{f}_{0,\infty})$ is weak mixing of order $n$, then so is $(X,f_{0,\infty})$ for any $n\geq2$; while there exists $(X,f_{0,\infty})$ such that it is weak mixing of order $2$ but $(\mathcal{M} (X),\hat{f}_{0,\infty})$ is not. We then prove that Li-Yorke chaos (resp., distributional chaos) of $(X,f_{0,\infty})$ carries over to $(\mathcal{M}(X),\hat f_{0,\infty})$, and give an example to show that $(X,f)$ and $(\mathcal{M}(X),\hat f)$ may have no Li-Yorke pair simultaneously. We also prove that if $f_n$ is surjective for all $n\geq 0$, then chain mixing of $(\mathcal{M}(X),\hat f_{0,\infty})$ always holds true, and shadowing of $(\mathcal{M}(X),\hat f_{0,\infty})$ implies mixing of $(X, f_{0,\infty})$.