AI 中文总结
该研究针对流自编码器的训练损失次优问题，提出归一化自编码器（NAE），采用条件损失对齐梯度，在多类基准任务上实现了最先进的生成性能。
AI 中文摘要
我们考虑带有近似逆的归一化流的设置，这是一种已确立的范式，涵盖全维度（$d=D$）和瓶颈（$d<D$）设置，并将这些模型归为流自编码器。我们对其训练动力学进行了理论研究，证明现有方法使用的损失是次优的；具体而言，编码器和解码器的替代损失必须与重构损失对齐优化。基于这些见解，我们提出归一化自编码器（Normalizing Autoencoder，NAE），其采用新颖的条件损失，使替代损失梯度与重构损失梯度对齐，直接改进了当前标准。在分子生成、表格数据和图像基准上的大量实验表明，NAE 达到了最先进的性能。我们的工作强调了流自编码器中损失对齐的重要性，并确立 NAE 为强大的生成框架。
英文摘要
We consider the setting of Normalizing flows with approximate inverses, an established paradigm spanning both full-dimensional ($d=D$) and bottleneck ($d<D$) settings, and group these models under the term flow autoencoders. We present a theoretical investigation into their training dynamics and prove that the proposed loss used by existing approaches is suboptimal; specifically, both encoder and decoder surrogates must be optimized in alignment with reconstruction loss. Guided by these insights, we propose Normalizing Autoencoder (NAE), which employs a novel conditional loss that aligns the surrogate loss gradient with that of reconstruction loss, directly improving upon the current standard. Extensive experiments across molecule generation, tabular data, and image benchmarks demonstrate that NAE achieves state of the art performance. Our work highlights the importance of loss alignment in flow autoencoders and establishes NAE as a powerful generative framework.
