通过数据缩放提升生成模型稳定性与质量，理论证明其调控偏差-方差权衡。
Scaling-based Data Augmentation for Generative Models and its Theoretical Extension
- 引入数据缩放与方差正则化，改进生成对抗训练稳定性
- 实验证明新方法在多个基准数据集上提升生成质量和学习稳定性
- 首次理论证明数据缩放影响估计误差的偏差-方差权衡，适合生成模型研究者
本文研究稳定生成模型的学习方法，以实现高质量数据生成。噪声注入常用于稳定训练，但合适噪声分布的选择仍具挑战。Diffusion-GAN 通过使用时间步依赖的判别器解决此问题。我们研究 Diffusion-GAN 发现，数据缩放是实现稳定学习与高质量生成的关键因素。基于此，提出 Scale-GAN 算法，结合数据缩放与方差正则化。进一步地，理论上证明数据缩放可控制估计误差界的偏差-方差权衡。作为理论延伸，考虑可逆数据增强下的 GAN 框架。在多个基准数据集上的对比实验表明，该方法显著提升了训练稳定性和生成准确性。
原文摘要 · Abstract (English)
This paper studies stable learning methods for generative models that enable high-quality data generation. Noise injection is commonly used to stabilize learning. However, selecting a suitable noise distribution is challenging. Diffusion-GAN, a recently developed method, addresses this by using the diffusion process with a timestep-dependent discriminator. We investigate Diffusion-GAN and reveal that data scaling is a key component for stable learning and high-quality data generation. Building on our findings, we propose a learning algorithm, Scale-GAN, that uses data scaling and variance-based regularization. Furthermore, we theoretically prove that data scaling controls the bias-variance trade-off of the estimation error bound. As a theoretical extension, we consider GAN with invertible data augmentations. Comparative evaluations on benchmark datasets demonstrate the effectiveness of our method in improving stability and accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。