Comment on "Why does deep and cheap learning work so well?" [arXiv: 1608.08225]

By David J. Schwab, Pankaj Mehta. 2016

25 citations recorded by the source corpus.

In a recent paper, "Why does deep and cheap learning work so well?", Lin and Tegmark claim to show that the mapping between deep belief networks and the variational renormalization group derived in [arXiv:1410.3831] is invalid, and present a "counterexample" that claims to show that this mapping does not hold. In this comment, we show that these claims are incorrect and stem from a misunderstanding of the variational RG procedure proposed by Kadanoff. We also explain why the "counterexample" of Lin and Tegmark is compatible with the mapping proposed in [arXiv:1410.3831].

Subfields: Developmental and Educational Psychology, Scaling & Learning Theory, Statistical Learning Theory