REVIEW 4 cited by
Posterior Sampling in High Dimension via Diffusion Processes
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
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.
Forward citations
Cited by 4 Pith papers
-
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.
-
The Entropic Signature of Class Speciation in Diffusion Models
Class-conditional entropy of noisy states peaks at a sharp speciation time in variance-preserving diffusion and can be estimated in trained models to localize semantic decisions during generation.
-
Sampling from Binary Quadratic Distributions via Stochastic Localization
Stochastic localization drives binary quadratic posteriors into a strong-field regime where Glauber, Metropolis-Hastings, and DULA-type samplers satisfy Poincaré inequalities with polynomial mixing time.
-
Memorization and Generalization in Generative Diffusion under the Manifold Hypothesis
For manifold-structured data, the authors derive explicit collapse (memorization) and optimal stopping times for empirical-score diffusion, showing the best generation occurs inside the memorization phase and the samp...
Discussion (0). Continue with ORCID to comment.