Sampling from Spherical Spin Glasses in Total Variation via Algorithmic Stochastic Localization
arxiv(2024)
摘要
We consider the problem of algorithmically sampling from the Gibbs measure of
a mixed p-spin spherical spin glass. We give a polynomial-time algorithm that
samples from the Gibbs measure up to vanishing total variation error, for any
model whose mixture satisfies
ξ”(s) < 1/(1-s)^2, ∀
s∈ [0,1).
This includes the pure p-spin glasses above a critical
temperature that is within an absolute (p-independent) constant of the
so-called shattering phase transition. Our algorithm follows the algorithmic
stochastic localization approach introduced in (Alaoui, Montanari, Sellke,
20022). A key step of this approach is to estimate the mean of a sequence of
tilted measures. We produce an improved estimator for this task by identifying
a suitable correction to the TAP fixed point selected by approximate message
passing (AMP). As a consequence, we improve the algorithm's guarantee over
previous work, from normalized Wasserstein to total variation error. In
particular, the new algorithm and analysis opens the way to perform inference
about one-dimensional projections of the measure.
更多查看译文
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要