“Approximate models”

Just saw the author present this in a lecture:

Here’s my summary of his chat:

Produces a frequentist-esque machinery, with different assumptions. You have no true models, no repeatability as such, but you can construct approximations for certain goals and with certain kinds of guarantee. Hard to see how you would extract a law of nature in this context, but it looks natural for machine learning problems. Assuming no good model rather than a contaminated model?

Obviously, I don’t know enough about this to say anything, but it looks interesting. However, it’s also a one-man shop.

Connection with learning theory?