Posterior sampling from the spiked models via diffusion processes

A Montanari, Y Wu - arXiv preprint arXiv:2304.11449, 2023 - arxiv.org
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 …

Low-rank combinatorial optimization and statistical learning by spatial photonic Ising machine

H Yamashita, K Okubo, S Shimomura, Y Ogura… - Physical Review Letters, 2023 - APS
The spatial photonic Ising machine (SPIM)[D. Pierangeli, Large-Scale Photonic Ising
Machine by Spatial Light Modulation, Phys. Rev. Lett. 122, 213902 (2019). PRLTAO 0031 …

Universality of spectral independence with applications to fast mixing in spin glasses

N Anari, V Jain, F Koehler, HT Pham, TD Vuong - Proceedings of the 2024 …, 2024 - SIAM
We study Glauber dynamics for sampling from discrete distributions μ on the hypercube {±1}
n. Recently, techniques based on spectral independence have successfully yielded optimal …

Optimality of Glauber dynamics for general-purpose Ising model sampling and free energy approximation

D Kunisky - Proceedings of the 2024 Annual ACM-SIAM …, 2024 - SIAM
Abstract Recently, Eldan, Koehler, and Zeitouni (2020) showed that Glauber dynamics
mixes rapidly for general Ising models so long as the difference between the largest and …

On sampling from ising models with spectral constraints

A Galanis, A Kalavasis, AV Kandiros - arXiv preprint arXiv:2407.07645, 2024 - arxiv.org
We consider the problem of sampling from the Ising model when the underlying interaction
matrix has eigenvalues lying within an interval of length $\gamma $. Recent work in this …

Learning Hard-Constrained Models with One Sample

A Galanis, A Kalavasis, AV Kandiros - Proceedings of the 2024 Annual ACM …, 2024 - SIAM
We consider the problem of estimating the parameters of a Markov Random Field with hard-
constraints using a single sample. As our main running examples, we use the k-SAT and the …

Trickle-Down in Localization Schemes and Applications

N Anari, F Koehler, TD Vuong - Proceedings of the 56th Annual ACM …, 2024 - dl.acm.org
Trickle-down is a phenomenon in high-dimensional expanders with many important
applications—for example, it is a key ingredient in various constructions of high-dimensional …

From sampling to optimization on discrete domains with applications to determinant maximization

N Anari, TD Vuong - Conference on Learning Theory, 2022 - proceedings.mlr.press
We establish a connection between sampling and optimization on discrete domains. For a
family of distributions $\mu $ defined on size $ k $ subsets of a ground set of elements, that …

Fast Mixing in Sparse Random Ising Models

K Liu, S Mohanty, A Rajaraman, DX Wu - arXiv preprint arXiv:2405.06616, 2024 - arxiv.org
Motivated by the community detection problem in Bayesian inference, as well as the recent
explosion of interest in spin glasses from statistical physics, we study the classical Glauber …

Complexity of high-dimensional identity testing with coordinate conditional sampling

A Blanca, Z Chen, D Štefankovič… - The Thirty Sixth …, 2023 - proceedings.mlr.press
We study the identity testing problem for high-dimensional distributions. Given as input an
explicit distribution $\mu $, an $\varepsilon> 0$, and access to sampling oracle (s) for a …