Deep Generative Learning via Variational Gradient Flow

Authors: Yuan Gao, Yuling Jiao, Yang Wang, Yao Wang, Can Yang, Shunkang Zhang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on benchmark datasets demonstrate that VGrow can generate high-fidelity images in a stable and efficient manner, achieving competitive performance with state-of-the-art GANs.
Researcher Affiliation Academia 1School of Mathematics and Statistics, Xi an Jiaotong University, China 2School of Statistics and Mathematics, Zhongnan University of Economics and Law, China and KLATASDSMOE, School of Statistics, East China Normal University, China 3Department of Mathematics, The Hong Kong University of Science and Technology, Hong Kong 4School of Management, Xi an Jiaotong University, China.
Pseudocode No The paper describes the 'VGrow learning procedure' in bullet points, but it is not formatted as pseudocode or an algorithm block.
Open Source Code Yes The code of VGrow is available at https://github. com/xjtuygao/VGrow.
Open Datasets Yes We test VGrow with the above-mentioned four divergences on four benchmark datasets including MNIST (Le Cun et al., 1998), Fashion MNIST (Xiao et al., 2017), CIFAR10 (Krizhevsky & Hinton, 2009) and Celeb A (Liu et al., 2015)
Dataset Splits No The paper mentions training and test sets with specific sizes but does not explicitly detail a separate validation set with split information.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory amounts) used for running experiments are provided in the paper.
Software Dependencies No The paper mentions 'tensorflow implementation' but does not specify a version number for TensorFlow or any other software dependencies.
Experiment Setup No The paper states that 'Implementation details can be found in the second and third section of the supplementary material' but does not provide specific hyperparameter values or detailed training configurations in the main text.