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 …
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 …
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
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 …
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 …
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 …
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 …
constraints using a single sample. As our main running examples, we use the k-SAT and the …
Trickle-Down in Localization Schemes and Applications
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 …
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
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 …
family of distributions $\mu $ defined on size $ k $ subsets of a ground set of elements, that …
Fast Mixing in Sparse Random Ising Models
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 …
explosion of interest in spin glasses from statistical physics, we study the classical Glauber …
Complexity of high-dimensional identity testing with coordinate conditional sampling
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 …
explicit distribution $\mu $, an $\varepsilon> 0$, and access to sampling oracle (s) for a …