REVIEW 4 cited by
Shattering in the Ising Pure $p$-Spin Model
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
We study the Ising pure $p$-spin model for large $p$. We investigate the landscape of the Hamiltonian of this model. We show that for any $\gamma>0$ and any large enough $p$, the model exhibits an intricate geometrical property known as the multi Overlap Gap Property above the energy value $\gamma\sqrt{2\ln 2}$. We then show that for any inverse temperature $\sqrt{\ln 2}<\beta<\sqrt{2\ln 2}$ and any large $p$, the model exhibits shattering: w.h.p. as $n\to\infty$, there exists exponentially many well-separated clusters such that (a) each cluster has exponentially small Gibbs mass, and (b) the clusters collectively contain all but a vanishing fraction of Gibbs mass. Moreover, these clusters consist of configurations with energy near $\beta$. Range of temperatures for which shattering occurs is within the replica symmetric region. To the best of our knowledge, this is the first shattering result regarding the Ising $p$-spin models. Our proof is elementary, and in particular based on simple applications of the first and the second moment methods.
Forward citations
Cited by 4 Pith papers
-
Sequential Dynamics in Ising Spin Glasses
Block-sequential updates on the SK model are exactly characterized by a system of integro-difference equations, conjectured to coincide with systematic scan dynamics as the block size vanishes.
-
Near-optimal shattering in the Ising pure p-spin and rarity of solutions returned by stable algorithms
Shattering in the Ising pure p-spin model is proved for all large p and all β between (1+ε)√(2 log p/p) and (1-ε)√(2 log 2), and stable algorithms are shown to land only in exponentially rare parts of the near-typical...
-
Learning the Sherrington-Kirkpatrick Model Even at Low Temperature
A simple subgaussian argument lets the Sparsitron algorithm recover SK model parameters in polynomial time for all beta <= sqrt(log n), breaking the beta=1 barrier.
-
Weak Poincar\'e Inequalities, Simulated Annealing, and Sampling from Spherical Spin Glasses
Simulated annealing provably samples spherical spin glass Gibbs measures up to the replica-symmetric threshold (SL) via a new weak-Poincaré-inequality framework, the first Markov chain guarantee past the uniqueness tr...
Discussion (0). Continue with ORCID to comment.