Not all Strongly Rayleigh Distributions Have Small Probabilistic Generating Circuits

Authors: Markus Bläser

ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical As our main result, we prove that this question has a negative answer. There are strongly Rayleigh distributions that cannot be represented by polynomial-sized probabilistic generating circuits, assuming a widely accepted complexity theoretic conjecture.
Researcher Affiliation Academia 1Saarland University, Saarland Informatics Campus, Saarbrücken, Germany.
Pseudocode No The paper does not contain any pseudocode or algorithm blocks. It is a theoretical paper focused on mathematical proofs.
Open Source Code No The paper does not provide any information about open-source code availability.
Open Datasets No The paper is theoretical and does not involve the use of datasets for training or any other purpose.
Dataset Splits No The paper is theoretical and does not involve dataset splits or validation procedures.
Hardware Specification No The paper is theoretical and does not describe any experimental setup or hardware used.
Software Dependencies No The paper is theoretical and does not mention any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not involve any experimental setup details, hyperparameters, or training configurations.