Breaking the curse of dimensionality in structured density estimation

Authors: Robert A. Vandermeulen, Wai Ming Tai, Bryon Aragam

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We do not have experimental results.
Researcher Affiliation Academia Much of this work was conducted at the Berlin Institute for the Foundations of Learning and Data (BIFOLD), Technische Universität Berlin. Contact: robert.anton.vandermeulen@gmail.com The work was done when the author was at Nanyang Technological University. Contact: taiwaiming2003@gmail.com University of Chicago. Contact: bryon@chicagobooth.edu
Pseudocode No The paper does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not state that source code for the methodology is provided or include a link to a code repository. The NeurIPS checklist confirms 'We do not have experimental results.' and thus no code is provided.
Open Datasets Yes Heatmaps of the magnitude of the correlation between red pixel and every other pixel, using the CIFAR-10 training set.
Dataset Splits No The paper is theoretical and does not describe experimental procedures involving training, validation, or test dataset splits.
Hardware Specification No The paper is theoretical and does not describe computational experiments, therefore, no hardware specifications are mentioned. The NeurIPS checklist confirms 'We do not have experimental results.' for this section.
Software Dependencies No The paper is theoretical and does not describe computational experiments, therefore, no specific software dependencies with version numbers are mentioned. The NeurIPS checklist confirms 'We do not have experimental results.' for this section.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with specific hyperparameters or training settings. The NeurIPS checklist confirms 'We do not have experimental results.' for this section.