Computational hardness of sampling beyond the shattering phase transition

Demonstrate the computational intractability of sampling from the Gibbs measure of mixed p-spin spherical spin glasses beyond the shattering (dynamical) phase transition, i.e., prove that sampling is fundamentally hard in the regime where the dynamical phase transition predicts slow dynamics.

Background

Beyond predictions for mixing behavior of Langevin dynamics, a stronger conjecture posits an inherent computational barrier to sampling from the Gibbs measure in the low-temperature (shattered) regime. Prior works have provided evidence of failure for certain classes of algorithms but a complete hardness result remains conjectural.

Establishing such hardness would align algorithmic limitations with the geometric complexity (shattering) of the Gibbs measure and solidify the link between thermodynamic transitions and computational barriers.

References

A bolder version of the dynamical phase transition conjecture postulates that not only Langevin dynamics is slow, but indeed sampling is fundamentally hard beyond the shattering phase transition.

— Sampling from Spherical Spin Glasses in Total Variation via Algorithmic Stochastic Localization  (2404.15651 - Huang et al., 2024) in Subsection 1.1 Background and related work

We leave open a proof of hardness for stable samplers throughout \beta > \beta_{dyn}(k, D).

— Gibbs Sampling in the Shattered Phase by Decoded Quantum Interferometry  (2609.40345 - Zhou et al., 30 Sep 2026) in Section 4, Stable Algorithms, Shattering, and Hardness of Sampling; paragraph following Theorem 3.1

For the dense k-spin model, no stable algorithms can efficiently Gibbs sample when \beta > \beta_{dyn}(k), where

— Gibbs Sampling in the Shattered Phase by Decoded Quantum Interferometry  (2609.40345 - Zhou et al., 30 Sep 2026) in Appendix F, Phase Transitions and Algorithmic Thresholds in Spin Glasses, subsection Dense k-spin Model: the D to infinity Limit

It is believed that Markov chain-based methods should fail to sample from the Gibbs distribution when the inverse temperature exceeds the shattering threshold $\beta_{\shatter}$, and the best sampling algorithms work up to a constant of the threshold . On the other hand, an algorithm for computing the partition function was given well beyond $\beta_{\shatter}$ up to the ``replica symmetric threshold'' in a work of , which suggests that spin glass models may exhibit phases where sampling is hard, but computing the partition function is tractable. However, this story was complicated by the recent work , which uses a quantum-inspired algorithm to sample in the shattered phase. We consider it an interesting direction to understand what the true algorithmic threshold is for sampling, as well as what the threshold is for Markov chains.

— Sampling from the Sherrington-Kirkpatrick Model up to Criticality  (2610.17717 - Du et al., 13 Oct 2026) in Section 1, Subsection 1.4, Future directions, Subsection “Counting vs. sampling in average-case models”