SpHMC: Spectral Hamiltonian Monte Carlo

Authors: Haoyi Xiong, Kafeng Wang, Jiang Bian, Zhanxing Zhu, Cheng-Zhong Xu, Zhishan Guo, Jun Huan5516-5524

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments have been conducted to evaluate the proposed algorithm using real-world datasets. The performance comparisons on three real-world applications demonstrate the superior performance of Sp HMC beyond baseline methods.
Researcher Affiliation Collaboration 1Big Data Lab, Baidu Inc. & National Engineering Laboratory for Deep Learning Technology and Applications, China 2Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, China 3Department of Electrical and Computer Engineering, University of Central Florida, United States 4Deep Learning Laboratory, Peking University & Beijing Institute of Big Data Research, China
Pseudocode Yes Algorithm 1 Spectral Sampler using Stochastic Gradient Hamiltonian Monte Carlo
Open Source Code No The paper does not provide an explicit statement or link for the open-source code of the described methodology.
Open Datasets Yes We propose to evaluate Sp HMC using three real-world benchmark datasets including MNIST, Fashion MNIST, and EMNIST
Dataset Splits No While the paper mentions "10 folder cross-validation on the training set" for hyper-parameter tuning, it does not explicitly provide the specific percentages or counts for training, validation, and test dataset splits needed to reproduce the experiment.
Hardware Specification No The paper does not provide any specific hardware details used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers).
Experiment Setup Yes All other parameters such as regularization term λ, step size η and batch size m for both Sp HMC and baselines are all tuned best with repeat trials.