Generalization, memorization, and overfitting for diffusion models trained in the lazy high-dimensional regime
惰性高维训练下扩散模型的泛化、记忆与过拟合
Modern score-based generative models have achieved remarkable empirical success in high-dimensional tasks such as image, audio, and video synthesis. These models reduce distribution learning to a sequence of regression problems that, if solved exactly on finite data, would ultimately reproduce the training samples. Their ability to generalize must therefore arise from the implicit or explicit regularization during training. In this work, we develop a generative counterpart…