Functional weak convergence of stochastic integrals for moving averages and continuous-time random walks

There is by now an extensive and well-developed theory of weak convergence for moving averages and continuous-time random walks (CTRWs) with respect to Skorokhod's M1 and J1 topologies. Here we address the fundamental question of how this translates into functional limit theorems, in the M1 or J1 topology, for stochastic integrals driven by these processes. As a key application, we provide weak approximation results for a general class of SDEs driven by time-changed L\'evy processes. Such SDEs and their associated fractional Fokker--Planck--Kolmogorov equations are central to models of anomalous diffusion in statistical physics, and our results provide a rigorous functional characterisation of these as continuum limits of the corresponding models driven by CTRWs. In regard to strictly M1 convergent moving averages and so-called correlated CTRWs, it turns out that the convergence of stochastic integrals can fail markedly. Nevertheless, we are able to identify natural classes of integrand processes for which the convergence holds. We end by showing that these results are general enough to yield functional limit theorems, in the M1 topology, for certain stochastic delay differential equations driven by moving averages.