Understanding VAEs in Fisher-Shannon Plane

Authors: Huangjie Zheng, Jiangchao Yao, Ya Zhang, Ivor W. Tsang, Jia Wang5917-5924

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

Reproducibility Variable Result LLM Response
Research Type Experimental Through extensive qualitative and quantitative experiments, we provide with a better comprehension of VAEs in tasks such as high-resolution reconstruction, and representation learning in the perspective of Fisher information and Shannon information.
Researcher Affiliation Academia Huangjie Zheng,1 Jiangchao Yao,1,2 Ya Zhang,1 Ivor W. Tsang,2 Jia Wang1 1Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, 2University of Technology Sydney
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide a statement or link indicating the open-sourcing of the code for the methodology described.
Open Datasets Yes The experiments are conducted on the MNIST dataset (Lecun et al. 1998) and the SVHN dataset (Netzer et al. 2011).
Dataset Splits Yes We follow the original partition to split the data as 50,000/10,000/10,000 for the training, validation and test.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup Yes For the architecture of inference network and generative network, we both deploy a 5-layers network. Since the impacts of fully-connected and convolution architecture do not differ much in the experiments, we here present results using the architecture as 5 full-connected layers of dimension 300. The latent code is of dimension 40.