cs.LGNov 9, 2026

Patching Up Circuit Learning via Parameter Sharing

Authors: Charles Bricout, Gennaro Gala, Viacheslav Borovitskiy, Antonio Vergari

Organizations: University of Edinburgh · Independent Researcher

Abstract

Probabilistic circuits (PCs) have emerged as generative models guaranteeing tractable probabilistic inference. However, tractability comes at the price of larger model sizes than in other generative models. As such, to scale PCs to high-dimensional data such as images, previous work has devised several parameter sharing techniques as well as fast evaluation protocols that consider learning PCs on independent image patches. In this work, we revisit this practice to highlight a surprising learnability issue: models that assume independence counterintuitively can yield better likelihoods than models that do not. To break this apparent bottleneck and to scale PCs further, we introduce a recursive parameter sharing construction (RePA) that fosters efficiency without assuming independence. We show empirically that RePA can greatly reduce time and memory consumption while yielding competitive likelihoods. Inspired by these results, we further generalize the approach to data modalities that do not inherently exhibit patch-structure (NoPA), such as tabular data, showing similar efficiency improvements, with marginal changes in likelihoods and sample quality on seven tabular datasets. Code available at https://github.com/april-tools/RePA.

Figures & tables

Appendix figures & tables27 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Building Expressive and Tractable Probabilistic Generative Models: A Review

    Feb 1, 2024Sahil Sidheekh, Sriraam NatarajanProbabilistic CircuitsGenerative Modeling

  2. PeTeR: Post-Training Robustification of Probabilistic Circuits

    Jul 8, 2026Adrian Ciotinga, Yeming Dai, YooJung ChoiDistribution Shift RobustnessProbabilistic Circuits

  3. The Expressivity Boundary of Probabilistic Circuits: A Comparison with Large Language Models

    May 13, 2026Zhiyu Zhao, Xuejie Liu, Muhan Zhang +1Probabilistic CircuitsAutoregressive Language Modeling