Why are large models necessary when we have a limited number of training examples?

In Goodfellow et al. book Deep Learning chapter 12.1.4 they write

These large models learn some function $$f(x)$$, but do so using many more parameters than are necessary for the task. Their size is necessary only due to the limited number of training examples.

I am not able to understand this. Large models are expressive, but if you train them on few examples they should also overfit.

So, what do the authors mean by saying large models are necessary precisely because of the limited number of training examples?

This seems to go against the spirit of using more bias when training data is limited.

Model compression is applicable when the size of the original model is driven primarily by a need to prevent overfitting. In most cases, the model with the lowest generalization error is an ensemble of several independently trained models. Evaluating all $$n$$ ensemble members is expensive. Sometimes, even a single model generalizes better if it is large (for example, if it is regularized with dropout).