Universality of Spectral Independence with Applications to Fast Mixing in Spin Glasses

07/19/2023
by   Nima Anari, et al.
0

We study Glauber dynamics for sampling from discrete distributions μ on the hypercube {± 1}^n. Recently, techniques based on spectral independence have successfully yielded optimal O(n) relaxation times for a host of different distributions μ. We show that spectral independence is universal: a relaxation time of O(n) implies spectral independence. We then study a notion of tractability for μ, defined in terms of smoothness of the multilinear extension of its Hamiltonian – logμ – over [-1,+1]^n. We show that Glauber dynamics has relaxation time O(n) for such μ, and using the universality of spectral independence, we conclude that these distributions are also fractionally log-concave and consequently satisfy modified log-Sobolev inequalities. We sharpen our estimates and obtain approximate tensorization of entropy and the optimal O(n) mixing time for random Hamiltonians, i.e. the classically studied mixed p-spin model at sufficiently high temperature. These results have significant downstream consequences for concentration of measure, statistical testing, and learning.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset