mlsanityData to 7 Oct 2026

Realizing GANs via a Tunable Loss Function

arXiv 2106.05232 ↗First posted 9 Jun 2021cs.LG cs.IT math.ITcited by 10

Not on the map. Why?

Abstract (arXiv)

We introduce a tunable GAN, called α-GAN, parameterized by α ∈ (0,∞], which interpolates between various f-GANs and Integral Probability Metric based GANs (under constrained discriminator set). We construct α-GAN using a supervised loss function, namely, α-loss, which is a tunable loss function capturing several canonical losses. We show that α-GAN is intimately related to the Arimoto divergence, which was first proposed by "Osterriecher (1996), and later studied by Liese and Vajda (2006). We also study the convergence properties of α-GAN. We posit that the holistic understanding that α-GAN introduces will have practical benefits of addressing both the issues of vanishing gradients and mode collapse.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 18 of its 41 references that are in the map. First posted on arXiv 9 Jun 2021.

Builds on

18 of 41 references.

References · 18

  1. 2016Improved Techniques for Training GANscited by 2,938
  2. 2017Improved Training of Wasserstein GANscited by 2,223
  3. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  4. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  5. 2017Geometric GANcited by 232
  6. 2016Unrolled Generative Adversarial Networkscited by 208
  7. 2017Generalization and Equilibrium in Generative Adversarial Nets (GANs)cited by 165
  8. 2015Training generative neural networks via Maximum Mean Discrepancy optimizationcited by 149
  9. 2018How Well Generative Adversarial Networks Learn Distributionscited by 78
  10. 2015How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?cited by 76
  11. 2019Stabilizing Generative Adversarial Networks: A Surveycited by 57
  12. 2017Sobolev GANcited by 29
6 more
  1. 2017Approximation and Convergence Properties of Generative Adversarial Learningcited by 28
  2. 2019A Tunable Loss Function for Robust Classification: Calibration, Landscape, and Generalizationcited by 23
  3. 2017Fisher GANcited by 22
  4. 2017McGan: Mean and Covariance Feature Matching GANcited by 21
  5. 2019A Tunable Loss Function for Binary Classificationcited by 11
  6. 2020On the alpha-loss Landscape in the Logistic Modelcited by 3

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 5; 2024: 1; 2025: 1.

10 papers.

  1. 2024Asymmetry of the Relative Entropy in the Regularization of Empirical Risk Minimizationcited by 6
  2. 2022α-GAN: Convergence and Estimation Guaranteescited by 5
  3. 2023Analysis of the Relative Entropy Asymmetry in the Regularization of Empirical Risk Minimizationcited by 5
  4. 2023Addressing GAN Training Instabilities via Tunable Classification Lossescited by 5
  5. 2022Renyi Fair Information Bottleneck for Image Classificationcited by 3
  6. 2023A Unifying Generator Loss Function for Generative Adversarial Networkscited by 3
  7. 2023(αD,αG)-GANs: Addressing GAN Training Instabilities via Dual Objectivescited by 2
  8. 2022Classification Utility, Fairness, and Compactness via Tunable Information Bottleneck and R'enyi Measurescited by 1
  9. 2023Smoothly Giving up: Robustness for Simple Modelscited by 0
  10. 2025α-GAN by R'enyi Cross Entropycited by 0