LLM Reasoning 相关度: 6/10

Geometry-Aware Probabilistic Circuits via Voronoi Tessellations

Sahil Sidheekh, Sriraam Natarajan
arXiv: 2603.11946v1 发布: 2026-03-12 更新: 2026-03-12

AI 摘要

提出基于Voronoi图的概率电路,提升几何建模能力并保持可推理性。

主要贡献

  • 将Voronoi图引入概率电路以提升几何建模能力
  • 提出保证上下界的近似推断框架
  • 定义VT结构条件以恢复精确可推断性
  • 提出Voronoi图的可微分松弛

方法论

结合Voronoi图与概率电路,设计近似推断和结构约束,并使用可微分松弛进行优化。

原文摘要

Probabilistic circuits (PCs) enable exact and tractable inference but employ data independent mixture weights that limit their ability to capture local geometry of the data manifold. We propose Voronoi tessellations (VT) as a natural way to incorporate geometric structure directly into the sum nodes of a PC. However, naïvely introducing such structure breaks tractability. We formalize this incompatibility and develop two complementary solutions: (1) an approximate inference framework that provides guaranteed lower and upper bounds for inference, and (2) a structural condition for VT under which exact tractable inference is recovered. Finally, we introduce a differentiable relaxation for VT that enables gradient-based learning and empirically validate the resulting approach on standard density estimation tasks.

标签

概率电路 Voronoi图 密度估计 几何建模 可微分松弛

arXiv 分类

cs.LG cs.AI