How Many Samples are Needed to Estimate a Convolutional Neural Network?

Authors: Simon S. Du, Yining Wang, Xiyu Zhai, Sivaraman Balakrishnan, Russ R. Salakhutdinov, Aarti Singh

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In Section 5, we use numerical experiments to verify our theoretical findings.
Researcher Affiliation Academia Simon S. Du Carnegie Mellon University Yining Wang* Carnegie Mellon University Xiyu Zhai Massachusetts Institute of Technology Sivaraman Balakrishnan Carnegie Mellon University Ruslan Salakhutdinov Carnegie Mellon University Aarti Singh Carnegie Mellon University
Pseudocode No The paper does not contain any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement about releasing open-source code or a link to a code repository.
Open Datasets No For all experiments, we let the ambient dimension d be 64 and the input distribution be Gaussian with mean 0 and identity covariance. This describes how data was generated rather than providing access to a publicly available dataset.
Dataset Splits No The paper does not provide specific details on training, validation, or test splits. It mentions "Number of Training Data" on the x-axis of plots, but no split percentages or counts are given.
Hardware Specification No The paper does not mention any specific hardware specifications (e.g., GPU models, CPU types, memory) used for running the experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers.
Experiment Setup No The paper mentions that for all experiments, the ambient dimension d is 64 and the input distribution is Gaussian. It also specifies filter sizes and stride sizes for different experiments (e.g., "Filter size m 2", "stride size s 1"). However, it does not explicitly provide hyperparameters like learning rates, batch sizes, optimizers, or number of epochs, which are typical for an experimental setup.