Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Augmented Neural ODEs
Authors: Emilien Dupont, Arnaud Doucet, Yee Whye Teh
NeurIPS 2019 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We ο¬rst compare the performance of Res Nets and NODEs on simple regression tasks. To provide a baseline, we not only train on g(x) but also on data which can be made linearly separable without altering the topology of the space (implying that Neural ODEs should be able to easily learn this function). To ensure a fair comparison, we run large hyperparameter searches for each model and repeat each experiment 20 times to ensure results are meaningful across initializations (see appendix for details). We show results for experiments with d = 1 and d = 2 in Fig. 5. |
| Researcher Affiliation | Academia | Emilien Dupont University of Oxford EMAIL Arnaud Doucet University of Oxford EMAIL Yee Whye Teh University of Oxford EMAIL |
| Pseudocode | No | No pseudocode or algorithm blocks found. |
| Open Source Code | Yes | (the code to reproduce all experiments in this paper is available at https://github.com/Emilien Dupont/augmented-neural-odes). |
| Open Datasets | Yes | We test this behavior on image data by training models on MNIST, CIFAR10, SVHN and 200 classes of 64 64 Image Net. |
| Dataset Splits | No | We train both NODEs and ANODEs on the training set and plot the evolution of the validation loss during training in Fig. 9. |
| Hardware Specification | No | No specific hardware details (like GPU/CPU models or cloud instance types) are provided for running experiments. |
| Software Dependencies | No | No specific software dependencies with version numbers are mentioned in the provided text. |
| Experiment Setup | No | The paper mentions 'large hyperparameter searches' and states 'Full training and architecture details can be found in the appendix', but these specific details are not provided in the main body of the paper. |