CerDEQ: Certifiable Deep Equilibrium Model

Authors: Mingjie Li, Yisen Wang, Zhouchen Lin

ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we try to demonstrate the effectiveness of our proposed method for training a certified deep equilibrium model and the advantages of Cer DEQ via experiments on CIFAR-10 and Tiny Image Net.
Researcher Affiliation Academia 1Key Lab. of Machine Perception (Mo E), School of Artificial Intelligence, Peking University. 2Institute for Artificial Intelligence, Peking University. 3Peng Cheng Laboratory.
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks labeled as such.
Open Source Code No The paper does not provide an explicit statement about the release of source code or a link to a code repository for the described methodology.
Open Datasets Yes We adopt two datasets, CIFAR-10 and Tiny Image Net, to demonstrate the effectiveness of our method.
Dataset Splits No The paper mentions training epochs ('70 epochs in total on CIFAR-10') and the use of datasets (CIFAR-10, Tiny Image Net), but it does not specify explicit training, validation, and test dataset splits (e.g., 80/10/10 split, or sample counts for each split).
Hardware Specification Yes All the experiments are run on the Py Torch platform with GTX1080Ti.
Software Dependencies No The paper mentions 'Py Torch platform' but does not specify its version number or any other software dependencies with their versions.
Experiment Setup Yes Other hyperparameters for the experiments can be found in Appendix E. Table 10. The hyper-paramters for Cer DEQ s certified training for CIFAR-10 and Tiny Image Net.