The Geometry of Deep Networks: Power Diagram Subdivision

Authors: Randall Balestriero, Romain Cosentino, Behnaam Aazhang, Richard Baraniuk

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Numerous numerical experiments support and extend our theoretical results.
Researcher Affiliation Academia Randall Balestriero, Romain Cosentino, Behnaam Aazhang, Richard G. Baraniuk Rice University Houston, Texas, USA
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not include any unambiguous statement about releasing code for the methodology described, nor does it provide a direct link to a source-code repository.
Open Datasets Yes Figure 3 visualizes the centroids of the cell containing a particular input signal for a Large Conv and Res Net DN trained on the CIFAR10 dataset (see Appendix C for details on the models plus additional figures).
Dataset Splits No Fig. 4 (and 6 in the Appendix) plots the distributions of the log distances from the training points in the CIFAR10 training set to their nearest region boundary... Red: Test set.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup No The paper does not contain specific experimental setup details such as concrete hyperparameter values, training configurations, or system-level settings in the main text.