Non-asymptotic Error Bounds for Bidirectional GANs

Authors: Shiao Liu, Yunfei Yang, Jian Huang, Yuling Jiao, Yang Wang

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We derive nearly sharp bounds for the bidirectional GAN (Bi GAN) estimation error under the Dudley distance between the latent joint distribution and the data joint distribution with appropriately specified architecture of the neural networks used in the model. To the best of our knowledge, this is the first theoretical guarantee for the bidirectional GAN learning approach.
Researcher Affiliation Academia Shiao Liu Department of Statistics and Actuarial Science, University of Iowa Iowa City, IA 52242, USA shiao-liu@uiowa.edu Yunfei Yang Department of Mathematics, The Hong Kong University of Science and Technology Clear Water Bay, Hong Kong, China yyangdc@connect.ust.hk Jian Huang Department of Statistics and Actuarial Science, University of Iowa Iowa City, IA 52242, USA jian-huang@uiowa.edu Yuling Jiao School of Mathematics and Statistics, Wuhan University Wuhan, Hubei, China 430072 yulingjiaomath@whu.edu.cn Yang Wang Department of Mathematics, The Hong Kong University of Science and Technology Clear Water Bay, Hong Kong, China yangwang@ust.hk
Pseudocode No The paper does not contain pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not provide any statement about releasing source code or a link to a code repository.
Open Datasets No No experiments were conducted or described in the paper, hence no datasets were used or made available.
Dataset Splits No No experiments were conducted or described in the paper, hence no training, validation, or test dataset splits are provided.
Hardware Specification No No experiments were conducted or described in the paper, hence no hardware specifications are provided.
Software Dependencies No No experiments were conducted or described in the paper, hence no software dependencies or versions are specified.
Experiment Setup No No experiments were conducted or described in the paper, hence no experimental setup details like hyperparameters or training settings are provided.