Perturbation Analysis of Neural Collapse

Authors: Tom Tirer, Haoxiang Huang, Jonathan Niles-Weed

ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We support our theory with experiments in practical deep learning settings.
Researcher Affiliation Academia 1Faculty of Engineering, Bar-Ilan University, Ramat Gan, Israel 2Courant Institute of Mathematical Sciences, New York University, NY, US.
Pseudocode No The paper does not contain any sections or figures explicitly labeled 'Pseudocode' or 'Algorithm'.
Open Source Code No The paper does not provide any statements about releasing code for the methodology or links to a code repository.
Open Datasets Yes We consider the CIFAR-10 dataset and train an MLP... We consider the CIFAR-10 dataset and examine how modifying the regularization hyperparameters affects the NC behavior of the widely used Res Net18 (He et al., 2016a)... In Figure 4 we consider the MNIST dataset with 3K training samples per class.
Dataset Splits No The paper mentions using 'training samples per class' for CIFAR-10 and MNIST, but it does not explicitly state the dataset splits (e.g., specific percentages for training, validation, and testing sets, or refer to standard predefined splits).
Hardware Specification No The paper does not provide specific hardware details such as GPU models, CPU types, or memory specifications used for running the experiments.
Software Dependencies No The paper mentions 'default Py Torch initialization' but does not specify version numbers for PyTorch or any other software dependencies.
Experiment Setup Yes Specifically, as a baseline hyperparameter setting, we consider one that is used in previous works (Papyan et al., 2020; Zhu et al., 2021): default Py Torch initialization of the weights, SGD optimizer with LR 0.05 that is divided by 10 every 40 epochs, momentum of 0.9, and WD of 5e-4 for all the network s parameters.