BOLT-GAN: Bayes-Optimal Loss for Stable GAN Training

Mohammadreza Tavasoli Naeini, Ali Bereyhi, Morteza Noshad, Ben Liang, Alfred O. Hero
10/29/2025
cs.LGcs.AIeess.SP

No confident code implementation found for this paper. 3 possible matches can be shown below.

Abstract

We introduce BOLT-GAN, a simple yet effective modification of the WGAN framework inspired by the Bayes Optimal Learning Threshold (BOLT). We show that with a Lipschitz continuous discriminator, BOLT-GAN implicitly minimizes a different metric distance than the Earth Mover (Wasserstein) distance and achieves better training stability. Empirical evaluations on four standard image generation benchmarks (CIFAR-10, CelebA-64, LSUN Bedroom-64, and LSUN Church-64) show that BOLT-GAN consistently outperforms WGAN, achieving 10-60% lower Frechet Inception Distance (FID). Our results suggest that BOLT is a broadly applicable principle for enhancing GAN training.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 3 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Universal Training of Neural Networks to Achieve Bayes Optimal Classification Accuracy

81% match2025

CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization

80% match1 repo32024

A New Formulation of Lipschitz Constrained With Functional Gradient Learning for GANs

79% match1 repo6612025

The GAN is dead; long live the GAN! A Modern GAN Baseline

79% match1 repo8762025

CKGAN: Training Generative Adversarial Networks Using Characteristic Kernel Integral Probability Metrics

79% match1 repo22025

Spider GAN: Leveraging Friendly Neighbors to Accelerate GAN Training

79% match1 repo42023

Cite this paper

@article{naeini2025boltgan,
  title  = {BOLT-GAN: Bayes-Optimal Loss for Stable GAN Training},
  author = {Mohammadreza Tavasoli Naeini and Ali Bereyhi and Morteza Noshad and Ben Liang and Alfred O. Hero},
  year   = {2025},
  eprint = {2510.25609},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.25609v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2510.25609.svg)](https://codeofpaper.com/paper/2510.25609)

Discussion