Probabilistic Generating Circuits - Demystified

Authors: Sanyam Agarwal, Markus Bläser

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical One main insight of this work is that the negative weights are the cause for the power of PGCs and not the different representation. PGCs are PCs in disguise: we show how to transform any PGC on binary variables into a PC with negative weights with only polynomial blowup. As our second main result, we show that there is a good reason for this: we prove that PGCs for categorical variables with larger image size do not support tractable marginalization unless NP = P.
Researcher Affiliation Academia 1Saarland University, Saarland Informatics Campus, Saarbr ucken, Germany. Correspondence to: Sanyam Agarwal <agarwal@cs.uni-saarland.de>, Markus Bl aser <mblaeser@cs.uni-saarland.de>.
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any links to open-source code or state that code is made publicly available for the described methodology.
Open Datasets No The paper focuses on theoretical analysis and does not use or train on datasets, thus no dataset availability information is provided.
Dataset Splits No The paper focuses on theoretical analysis and does not involve data processing with training, validation, or test splits.
Hardware Specification No The paper is theoretical and does not describe computational experiments that would require specific hardware specifications.
Software Dependencies No The paper is theoretical and does not describe computational experiments that would require specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe experimental setups, hyperparameters, or training configurations.