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.

翻译：本文提出BOLT-GAN，这是一种受贝叶斯最优学习阈值（BOLT）启发、对WGAN框架进行简单而有效的改进方法。我们证明，在判别器满足Lipschitz连续性的条件下，BOLT-GAN隐式地最小化了一种不同于推土机（Wasserstein）距离的度量距离，并实现了更好的训练稳定性。在四个标准图像生成基准数据集（CIFAR-10、CelebA-64、LSUN Bedroom-64和LSUN Church-64）上的实证评估表明，BOLT-GAN始终优于WGAN，其弗雷歇初始距离（FID）降低了10-60%。我们的结果表明，BOLT是一种广泛适用于增强GAN训练的原则。