Machine learning and the Continuum Hypothesis

Abstract

We comment on a recent paper that connects certain forms of machine learning to Set Theory. We point out that part of the set-theoretic machinery is related to a result of Kuratowski about decompositions of finite powers of sets and we show that there is no Borel measurable monotone compression function on the unit interval.

arXiv commentversion 2: some simplifications version 3: expanded presentation with more comments

Cited by in corpus (1)

• A learning problem whose consistency is equivalent to the non-existence of real-valued measurable cardinals