扩散模型的泛化源于平衡表示空间
Generalization of Diffusion Models Arises with a Balanced Representation Space
AI总结：
通过分析两层ReLU去噪自编码器，证明记忆化导致局部尖峰表示，而泛化产生平衡表示，并在真实扩散模型中验证，提出基于表示的检测和编辑方法。
摘要：
扩散模型擅长生成高质量、多样化的样本，但当过度拟合训练目标时，它们有记忆训练数据的风险。我们通过表示学习的视角分析了扩散模型中记忆化和泛化之间的区别。通过研究两层ReLU去噪自编码器（DAE），我们证明了（i）记忆化对应于模型在学习的权重中存储原始训练样本以进行编码和解码，产生局部尖峰表示，而（ii）泛化发生在模型捕获局部数据统计时，产生平衡表示。此外，我们在真实的无条件和文本到图像扩散模型上验证了这些理论发现，表明相同的表示结构出现在深度生成模型中，并具有重要的实际意义。基于这些见解，我们提出了一种基于表示的检测记忆化的方法，以及一种无需训练的编辑技术，通过表示引导实现精确控制。总之，我们的结果强调了学习好的表示对于新颖且有意义的生成建模至关重要。
英文摘要：
Diffusion models excel at generating high-quality, diverse samples, yet they risk memorizing training data when overfit to the training objective. We analyze the distinctions between memorization and generalization in diffusion models through the lens of representation learning. By investigating a two-layer ReLU denoising autoencoder (DAE), we prove that (i) memorization corresponds to the model storing raw training samples in the learned weights for encoding and decoding, yielding localized spiky representations, whereas (ii) generalization arises when the model captures local data statistics, producing balanced representations. Furthermore, we validate these theoretical findings on real-world unconditional and text-to-image diffusion models, demonstrating that the same representation structures emerge in deep generative models with significant practical implications. Building on these insights, we propose a representation-based method for detecting memorization and a training-free editing technique that allows precise control via representation steering. Together, our results highlight that learning good representations is central to novel and meaningful generative modeling.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
