A Primal-Dual link between GANs and Autoencoders

Authors: Hisham Husain, Richard Nock, Robert C. Williamson

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

Reproducibility Variable Result LLM Response
Research Type Theoretical In this work, we study the f-GAN and WAE models and make two main discoveries. First, we find that the f-GAN and WAE objectives partake in a primal-dual relationship and are equivalent under some assumptions, which then allows us to explicate the success of WAE. Second, the equivalence result allows us to, for the first time, prove generalization bounds for Autoencoder models, which is a pertinent problem when it comes to theoretical analyses of generative models.
Researcher Affiliation Academia Hisham Husain , Richard Nock , , Robert C. Williamson , The Australian National University, Data61, The University of Sydney firstname.lastname@{data61.csiro.au,anu.edu.au}
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper is theoretical and does not mention releasing any source code for its methodology.
Open Datasets No The paper is theoretical and does not perform experiments using specific datasets. It mentions empirical distributions in the context of theoretical bounds but not for actual data training.
Dataset Splits No The paper is theoretical and does not describe any experimental setups or dataset splits for validation.
Hardware Specification No The paper is theoretical and does not describe any experimental hardware specifications.
Software Dependencies No The paper is theoretical and does not describe any software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe any experimental setup details such as hyperparameters or training configurations.