ANODEV2: A Coupled Neural ODE Framework
Authors: Tianjun Zhang, Zhewei Yao, Amir Gholami, Joseph E. Gonzalez, Kurt Keutzer, Michael W. Mahoney, George Biros
NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We present empirical results using several different configurations of ANODEV2, testing them on multiple models on CIFAR-10. We report results showing that this coupled ODE-based framework is indeed trainable, and that it achieves higher accuracy, as compared to the baseline models as well as the recently-proposed Neural ODE approach. |
| Researcher Affiliation | Academia | 1University of California at Berkeley, 2University of Texas at Austin, 3ICSI {tianjunz, zheweiy, amirgh, keutzer, jegonzal, and mahoneymw}@berkeley.edu, biros@ices.utexas.edu |
| Pseudocode | No | The paper describes its methodology using mathematical equations and textual explanations, but it does not include any pseudocode or algorithm blocks. |
| Open Source Code | No | We have open sourced the implementation of the coupled framework in Pytorch which allows general evolution operators (and not just the reaction-diffusion-advection)... The code is available in [10]. [10] Anonymized for review, Nov. 2019. |
| Open Datasets | Yes | We report the results of ANODEV2 for the two configurations discussed in section 2, on CIFAR-10 dataset which consists of 60,000 32 32 colour images in 10 classes. |
| Dataset Splits | No | The paper states it uses CIFAR-10 and mentions 'training settings' but does not explicitly provide details about train, validation, or test dataset splits (e.g., percentages or counts). |
| Hardware Specification | Yes | We would like to thank the Intel VLAB team for providing us with access to their computing cluster. We also gratefully acknowledge the support of NVIDIA Corporation for their donation of two Titan Xp GPU used for this research. |
| Software Dependencies | No | The framework is developed as a library in Py Torch and uses the checkpointing method proposed in [9]... The paper mentions 'PyTorch' but does not specify its version or any other software dependencies with version numbers. |
| Experiment Setup | No | The paper states 'See Appendix B and Appendix A.1 for the details of model architectures and training settings,' but these details are not provided in the main text itself, nor are the appendices fully included in the provided document for verification. |