Sampling from spherical spin glasses: diffusions and simulated annealing

The talk studies sampling from mean-field spin-glass Gibbs distributions above a stochastic-localization temperature threshold. It establishes total-variation guarantees for denoising diffusion and proves success of simulated annealing through a local-to-global principle. The results extend beyond worst-case uniqueness guarantees and approach the conjectured computational threshold for pure p-spin models up to a constant factor.