For any fixed β, there exists a system-size-independent external field θ such that Glauber dynamics on the SK model mixes in polynomial time with high probability.
arXiv preprint arXiv:2304.11449 , year=
3 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
3
Pith papers citing it
2
external citations · Pith
abstract
Sampling from the posterior is a key technical problem in Bayesian statistics. Rigorous guarantees are difficult to obtain for Markov Chain Monte Carlo algorithms of common use. In this paper, we study an alternative class of algorithms based on diffusion processes and variational methods. The diffusion is constructed in such a way that, at its final time, it approximates the target posterior distribution. The drift of this diffusion is given by the posterior expectation of the unknown parameter vector ${\boldsymbol \theta}$ given the data and the additional noisy observations. In order to construct an efficient sampling algorithm, we use a simple Euler discretization of the diffusion process, and leverage message passing algorithms and variational inference techniques to approximate the posterior expectation oracle. We apply this method to posterior sampling in two canonical problems in high-dimensional statistics: sparse regression and low-rank matrix estimation within the spiked model. In both cases we develop the first algorithms with accuracy guarantees in the regime of constant signal-to-noise ratios.
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Pattern formation in trained diffusion models emerges from out-of-equilibrium phase transitions driven by instabilities in low-frequency denoising modes linked to data symmetries and architectural constraints.
Establishes robustness of distribution support for guided diffusion processes under exact score access across DDIM, DDPM, and exponential integrator discretizations.
citing papers explorer
-
Mixing of Glauber Dynamics on High Overlap Gibbs Measures
For any fixed β, there exists a system-size-independent external field θ such that Glauber dynamics on the SK model mixes in polynomial time with high probability.
-
How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion Models
Pattern formation in trained diffusion models emerges from out-of-equilibrium phase transitions driven by instabilities in low-frequency denoising modes linked to data symmetries and architectural constraints.
-
On the Robustness of Distribution Support under Diffusion Guidance
Establishes robustness of distribution support for guided diffusion processes under exact score access across DDIM, DDPM, and exponential integrator discretizations.