The Limits of Tractable Marginalization

Authors: Oliver Broadrick, Sanyam Agarwal, Guy Van Den Broeck, Markus Bläser

ICML 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper presents theoretical results related to complexity classes, proofs of propositions and theorems, and definitions of computational problems like marginalization. There is no mention of empirical studies, datasets, experimental results, or performance metrics. For example, Section 4.1 is titled 'Separating PHM from PM with CSPs' and describes constructing functions and proving their complexity properties assuming complexity-theoretic conjectures.
Researcher Affiliation Academia 1Department of Computer Science, University of California, Los Angeles, United States 2Department of Computer Science, Saarland University, Saarbr ucken, Germany. Correspondence to: Oliver Broadrick <EMAIL>, Sanyam Agarwal <EMAIL>.
Pseudocode No The paper defines concepts, theorems, propositions, and proofs related to complexity theory and arithmetic circuits. It does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any explicit statements about releasing code, nor does it provide links to any code repositories.
Open Datasets No The paper is theoretical and focuses on complexity analysis of functions and circuits; it does not use any datasets for experiments or provide information about open datasets.
Dataset Splits No As no datasets are used for empirical evaluation, there is no mention of training/test/validation dataset splits.
Hardware Specification No The paper describes theoretical work and does not involve any experimental setup that would require specific hardware, therefore no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not describe any experimental implementation or software dependencies with specific version numbers.
Experiment Setup No The paper is theoretical and focuses on complexity analysis; it does not contain details about experimental setup, hyperparameters, or training configurations.