arXiv:2603.22468stat.MLcs.LG2026-03

用随机偏微分方程方法,分析非参数贝叶斯后验收缩速率和拉普拉斯近似。

SPDE Methods for Nonparametric Bayesian Posterior Contraction and Laplace Approximation

  • 将扩散框架扩展到无限维希尔伯特空间,用SPDE表示后验分布。
  • 在多种正则性和似然曲率条件下,得到非渐近的希尔伯特范数收缩率。
  • 适用于非参数线性高斯反问题,适合研究后验集中与贝叶斯推断理论者。

我们通过将Mou等(2024)基于扩散的框架推广至无限维情形,推导了非参数贝叶斯模型的后验收缩率(PCR)和有限样本伯恩斯坦-冯·米塞斯(BvM)结果。后验被表示为定义在可分希尔伯特空间上的朗之万随机偏微分方程(SPDE)的不变测度,从而可在多种似然曲率与正则性条件下控制后验矩,并获得希尔伯特范数下的非渐近浓度速率。我们还建立了后验的定量拉普拉斯近似。该理论在非参数线性高斯反问题中得以验证。

原文摘要 · Abstract (English)

We derive posterior contraction rates (PCRs) and finite-sample Bernstein von Mises (BvM) results for non-parametric Bayesian models by extending the diffusion-based framework of Mou et al. (2024) to the infinite-dimensional setting. The posterior is represented as the invariant measure of a Langevin stochastic partial differential equation (SPDE) on a separable Hilbert space, which allows us to control posterior moments and obtain non-asymptotic concentration rates in Hilbert norms under various likelihood curvature and regularity conditions. We also establish a quantitative Laplace approximation for the posterior. The theory is illustrated in a nonparametric linear Gaussian inverse problem.

贝叶斯推断后验收缩随机偏微分方程非参数统计

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。