Uploaded August 2026 | Updated November 2026, 5 days ago
Holden Lee (Johns Hopkins University)
https://simons.berkeley.edu/talks/holden-lee-johns-hopkins-university-2026-08-06
Diffusion Generative Modeling: Progress and Next Steps
We give a polynomial-time algorithm to sample from the Gibbs measure of the Sherrington-Kirkpatrick (SK) model--a key model arising from statistical physics--with negligible total-variation distance up to inverse temperature β<1/2. The algorithm is based on algorithmic stochastic localization (a.k.a. a diffusion model) and Jarzynski's equality with rejection sampling. The proof is based on the potential Hessian ascent framework previously developed for optimization, combining a covariance estimate of tilted Gibbs distribution via Gaussian integration by parts, overlap concentration, and precise cavity estimates; a free probability argument controlling the diagonal sub-algebra of the Hessian; and functional inequalities for the localized distributions. Prior work obtained TV distance error guarantees only up to β ≈ 0.295, while results covering the entire replica-symmetric regime β < 1 gave guarantees only in non-trivial Wasserstein distance. We then show how to use regularity properties of the diffusion process in order to conclude a weak Poincare inequality for the SK model and simplify the algorithm. Our work shows how the theory of diffusion models can be used to solve challenging problems about sampling. Joint work with Ewan Davies, Juspreet Singh Sandhu, and Jonathan Shi.
Holden Lee (Johns Hopkins University)
https://simons.berkeley.edu/talks/holden-lee-johns-hopkins-university-2026-08-06
Diffusion Generative Modeling: Progress and Next Steps
We give a polynomial-time algorithm to sample from the Gibbs measure of the Sherrington-Kirkpatrick (SK) model--a key model arising from statistical physics--with negligible total-variation distance up to inverse temperature β<1/2. The algorithm is based on algorithmic stochastic localization (a.k.a. a diffusion model) and Jarzynski's equality with rejection sampling. The proof is based on the potential Hessian ascent framework previously developed for optimization, combining a covariance estimate of tilted Gibbs distribution via Gaussian integration by parts, overlap concentration, and precise cavity estimates; a free probability argument controlling the diagonal sub-algebra of the Hessian; and functional inequalities for the localized distributions. Prior work obtained TV distance error guarantees only up to β ≈ 0.295, while results covering the entire replica-symmetric regime β < 1 gave guarantees only in non-trivial Wasserstein distance. We then show how to use regularity properties of the diffusion process in order to conclude a weak Poincare inequality for the SK model and simplify the algorithm. Our work shows how the theory of diffusion models can be used to solve challenging problems about sampling. Joint work with Ewan Davies, Juspreet Singh Sandhu, and Jonathan Shi.










