研究人员开发了一个新的几何框架来分析有限高斯混合模型中参数估计的收敛速率。该框架利用 Hellinger 下界将密度差异与 Wasserstein 距离联系起来，明确考虑了分量分离和最小权重。研究表明，当分量数量已知时，收敛主要由这些分量的空间排列决定。然而，当分量数量未知或被过度指定时，最小混合权重与收敛速率无关，将复杂性转移到二阶 Wasserstein 几何学。 AI
排序理由 该集群包含一篇详细介绍统计学新理论研究的学术论文。[lever_c_demoted from research: ic=2 ai=0.4]
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.16179v1 Announce Type: cross Abstract: We study an open problem of understanding the effects of the minimum component separation on the convergence rates of parameter estimation in finite Gaussian mixtures. We address this by developing a unified geometric framework ba…
We study an open problem of understanding the effects of the minimum component separation on the convergence rates of parameter estimation in finite Gaussian mixtures. We address this by developing a unified geometric framework based on novel Hellinger lower bounds that directly …