How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?

Authors: Zixiang Chen, Yuan Cao, Difan Zou, Quanquan Gu

ICLR 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we conduct some simple experiments to validate our theory. Since our paper mainly focuses on binary classification, we use a subset of the original CIFAR10 dataset (Krizhevsky et al., 2009), which only has two classes of images.
Researcher Affiliation Academia Department of Computer Science, University of California, Los Angles {chenzx19,yuancao,knowzou,qgu}@cs.ucla.edu
Pseudocode Yes Algorithm 1 Gradient descent with random initialization
Open Source Code No The paper does not contain any explicit statement about providing open-source code for the described methodology, nor does it provide a link to a code repository.
Open Datasets Yes we use a subset of the original CIFAR10 dataset (Krizhevsky et al., 2009)
Dataset Splits No The paper mentions using a subset of CIFAR10 for training and evaluating training error but does not specify any explicit training/validation/test dataset splits (e.g., percentages, counts, or predefined splits).
Hardware Specification No The paper does not provide any specific hardware details (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library names with versions) needed to replicate the experiment.
Experiment Setup No The paper mentions training a '5-layer fully-connected Re LU network' and varying 'sample sizes' but does not provide specific hyperparameters such as learning rate, batch size, optimizer, or number of epochs for the experimental setup.