On sampling from Ising models with spectral constraints
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 …
Weak Poincar\'e Inequalities, Simulated Annealing, and Sampling from Spherical Spin Glasses
There has been a recent surge of powerful tools to show rapid mixing of Markov chains, via
functional inequalities such as Poincar\'e inequalities. In many situations, Markov chains fail …
functional inequalities such as Poincar\'e inequalities. In many situations, Markov chains fail …
Locally Stationary Distributions: A Framework for Analyzing Slow-Mixing Markov Chains
K Liu, S Mohanty, P Raghavendra… - arXiv preprint arXiv …, 2024 - arxiv.org
Many natural Markov chains fail to mix to their stationary distribution in polynomially many
steps. Often, this slow mixing is inevitable since it is computationally intractable to sample …
steps. Often, this slow mixing is inevitable since it is computationally intractable to sample …
Stochastic Localization with Non-Gaussian Tilts and Applications to Tensor Ising Models
D Mikulincer, A Piana - arXiv preprint arXiv:2412.12720, 2024 - arxiv.org
We present generalizations and modifications of Eldan's Stochastic Localization process,
extending it to incorporate non-Gaussian tilts, making it useful for a broader class of …
extending it to incorporate non-Gaussian tilts, making it useful for a broader class of …