f-GANs in an Information Geometric Nutshell

Authors: Richard Nock, Zac Cranko, Aditya K. Menon, Lizhen Qu, Robert C. Williamson

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We also provide experiments1 that display the uplift that can be obtained through a principled design of the activation function (generator), or tuning of the link function (discriminator).The code used for our experiments is available through https://github.com/qulizhen/fgan_info_geometricSection 6 Experiments
Researcher Affiliation Collaboration Data61, the Australian National University and the University of Sydney {firstname.lastname, aditya.menon, bob.williamson}@data61.csiro.au
Pseudocode No The paper contains no structured pseudocode or algorithm blocks.
Open Source Code Yes 1The code used for our experiments is available through https://github.com/qulizhen/fgan_info_geometric
Open Datasets Yes Our datasets are MNIST [19] and LSUN tower category [38].
Dataset Splits No The paper states the datasets used but does not explicitly provide specific train/validation/test dataset splits. It mentions a supplement (SM) provides the proof of the results in the main file and additional experiments which might contain this information, but it's not in the provided text.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers.
Experiment Setup No The paper mentions using same hyperparameters as for generators and Re LU activation for all hidden layer activation of generators, but does not provide specific hyperparameter values or detailed training configurations.