Chi-square Generative Adversarial Network

Authors: Chenyang Tao, Liqun Chen, Ricardo Henao, Jianfeng Feng, Lawrence Carin Duke

ICML 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments show that the proposed procedure improves stability and convergence, and yields state-of-art results on a wide range of generative modeling tasks.
Researcher Affiliation Academia 1Electrical & Computer Engineering, Duke University, Durham, NC 27708, USA 2ISTBI, Fudan University, Shanghai, China.
Pseudocode Yes Algorithm 1 χ2 GAN. Input: data {xi}, batchsize b, decay ρ, learning rate δ. for t = 1, 2, 3, . . . do...
Open Source Code Yes Details of the experimental setup are in the SM, and code for our experiments are available from https://www.github.com/ chenyang-tao/chi2gan.
Open Datasets Yes MNIST We used the binarized MNIST in this experiment and compared with the results from prior results in Table 1.
Dataset Splits No The paper mentions training and testing on standard datasets (e.g., MNIST, CIFAR-10), but it does not provide specific details on the training, validation, and test splits (e.g., exact percentages or sample counts).
Hardware Specification Yes All experiments are implemented with Tensorflow and run on a single NVIDIA TITAN X GPU.
Software Dependencies No All experiments are implemented with Tensorflow and run on a single NVIDIA TITAN X GPU.
Experiment Setup No In all experiments we have used Xaiver initialization and Adam optimizer.