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 Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Neural Tangent Kernel Maximum Mean Discrepancy
Authors: Xiuyuan Cheng, Yao Xie
NeurIPS 2021 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Numerical experiments on synthetic and real-world datasets validate the theory and demonstrate the effectiveness of the proposed NTK-MMD statistic. |
| Researcher Affiliation | Academia | Xiuyuan Cheng Department of Mathematics Duke University EMAIL Yao Xie H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology EMAIL |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | 1Code available at https://github.com/xycheng/NTK-MMD/. |
| Open Datasets | Yes | We take the original MNIST dataset, which contains 28 × 28 gray-scale images... The Microsoft Research Cambridge-12 (MSRC-12) Kinect gesture dataset [18]. |
| Dataset Splits | No | The paper mentions splitting data into training and test sets but does not explicitly state a validation set or its split. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. |
| Software Dependencies | No | The paper mentions using a '2-layer network' and 'soft-plus activation', and refers to 'SGD' and 'Adam' optimizers, but does not specify software names with version numbers (e.g., PyTorch 1.x, Python 3.x). |
| Experiment Setup | Yes | The online training is of 1 epoch (1 pass over the training set) with batch-size = 1. The bootstrap estimate of test threshold uses nboot = 400 permutations. The testing power is approximated by nrun = 500 Monte Carlo replicas... using a 2-layer network (1 hidden layer) with soft-plus activation. |