[D] Complexity of Time Series Models: ARIMA vs. LSTM

In statistical learning theory, there is something called the VC Dimension of an algorithm (https://en.m.wikipedia.org/wiki/Vapnik%E2%80%93Chervonenkis_dimension) - the VC dimension is apparently what describes the relartive level of complexity a machine learning algorithm can capture. Does this concept of VC Dimension carry over to models in time series analysis? Is it possible to show that LSTM's have a higher VC dimension compared to ARIMA style models? Supposedly, neural network based time series models were developed because modeols like ARIMA was unable to provide reliable estimates for bigger and complex datasets. Mathematically speaking, what allows a LSTM to capture more variation and complexity in a dataset compared to ARIMA?