mlsanityData to 7 Oct 2026

Reparameterized Sampling for Generative Adversarial Networks

arXiv 2107.00352 ↗First posted 1 Jul 2021stat.ML cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Recently, sampling methods have been successfully applied to enhance the sample quality of Generative Adversarial Networks (GANs). However, in practice, they typically have poor sample efficiency because of the independent proposal sampling from the generator. In this work, we propose REP-GAN, a novel sampling method that allows general dependent proposals by REParameterizing the Markov chains into the latent space of the generator. Theoretically, we show that our reparameterized proposal admits a closed-form Metropolis-Hastings acceptance ratio. Empirically, extensive experiments on synthetic and real datasets demonstrate that our REP-GAN largely improves the sample efficiency and obtains better sample quality simultaneously.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 22 of its 29 references that are in the map. First posted on arXiv 1 Jul 2021.

Builds on

22 of 29 references.

References · 22

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2013Auto-Encoding Variational Bayescited by 3,980
  3. 2016Improved Techniques for Training GANscited by 2,938
  4. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  5. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  6. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  7. 2017Wasserstein GANcited by 635
  8. 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 284
  9. 2016Unrolled Generative Adversarial Networkscited by 208
  10. 2019NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transportcited by 73
  11. 2020Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Samplingcited by 71
  12. 2016Normalizing Flows on Riemannian Manifoldscited by 68
10 more
  1. 2017Generalizing Hamiltonian Monte Carlo with Neural Networkscited by 52
  2. 2018Discriminator Rejection Samplingcited by 48
  3. 2018Metropolis-Hastings Generative Adversarial Networkscited by 40
  4. 2017A-NICE-MC: Adversarial Training for MCMCcited by 36
  5. 2019Discriminator optimal transportcited by 25
  6. 2017Approximate Inference with Amortised MCMCcited by 22
  7. 2016An introduction to sampling via measure transportcited by 16
  8. 2017Learning Model Reparametrizations: Implicit Variational Inference by Fitting MCMC distributionscited by 7
  9. 2020Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminatorcited by 7
  10. 2020Lessons Learned from the Training of GANs on Artificial Datasetscited by 5

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 1.

2 papers.

  1. 2024Do Generated Data Always Help Contrastive Learning?cited by 25
  2. 2022Mining Multi-Label Samples from Single Positive Labelscited by 1