Geometry-Aware Probabilistic Circuits via Voronoi Tessellations

📰 ArXiv cs.AI

arXiv:2603.11946v2 Announce Type: replace-cross Abstract: 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, na\"ively introducing such structure breaks tractability. We formalize this incompatibility and develop two complementary s

Published 2 Jun 2026

Full Article

Title: Geometry-Aware Probabilistic Circuits via Voronoi Tessellations

Abstract:
arXiv:2603.11946v2 Announce Type: replace-cross Abstract: 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, na\"ively introducing such structure breaks tractability. We formalize this incompatibility and develop two complementary s
Read full paper → ← Back to Reads