非负矩阵分解的奇异性及其在贝叶斯推断中的应用
Singularities of Non-negative Matrix Factorization and their application to Bayesian inference
浏览论文内容
中文总结 AI 辅助
本文研究非负矩阵分解的奇异性,推导其实对数规范阈值的上界,并给出特定条件下的精确值,从而界定贝叶斯泛化误差与自由能的首项系数。
中文摘要 AI 辅助
非负矩阵分解(NMF)是一种奇异统计模型,其贝叶斯渐近行为由实对数规范阈值(RLCT)控制。我们研究分解映射的局部几何结构,并推导出NMF的RLCT的一个上界。设$H$为模型内维数,$H_0$为真实$M\times N$矩阵的非负秩。假设真实矩阵在参数域内部允许一个内维数为$H_0$的严格正分解,我们证明,对于光滑正先验,有$\lambda\leq \{(H-H_0)\min(M,N)+H_0(M+N-H_0)\}/2$。当$H_0\geq3$时,该界严格优于之前的界。证明使用了局部解析规范形式,将独立的线性坐标与残差矩阵乘积分离。当$H=H_0$且等于真实矩阵的普通秩时,我们得到精确值$\lambda=H_0(M+N-H_0)/2$。在奇异学习理论的标准假设下,这些结果界定了期望贝叶斯泛化误差和贝叶斯自由能的首项系数。
英文摘要
Non-negative matrix factorization (NMF) is a singular statistical model whose Bayesian asymptotics are governed by the real log canonical threshold (RLCT). We study the local geometry of the factorization map and derive an upper bound for the RLCT of NMF. Let $H$ be the model inner dimension and $H_0$ the non-negative rank of the true $M\times N$ matrix. Assuming that the true matrix admits a strictly positive factorization of inner dimension $H_0$ in the interior of the parameter domain, we prove, for smooth positive priors, that $λ\leq \{(H-H_0)\min(M,N)+H_0(M+N-H_0)\}/2$. This bound strictly improves the previous bound when $H_0\geq3$. The proof uses a local analytic normal form that separates independent linear coordinates from a residual matrix product. When $H=H_0$ also equals the ordinary rank of the true matrix, we obtain the exact value $λ=H_0(M+N-H_0)/2$. Under the standard assumptions of singular learning theory, these results bound the leading coefficients of the expected Bayesian generalization error and the Bayesian free energy.
发表机构
- Toyota Central R&D Labs., Inc.(丰田中央研发实验室有限公司)
机构由 AI 辅助整理,请以论文原文为准。