Neural Tangent Kernel Maximum Mean Discrepancy

Authors: Xiuyuan Cheng, Yao Xie

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | 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 xiuyuan.cheng@duke.edu Yao Xie H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology yao.xie@isye.gatech.edu
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.