提出新方法提升结构化数据生成质量与速度
Latent Nonlinear Denoising Score Matching for Enhanced Learning of Structured Distributions
- 结合非线性前向过程与变分自编码框架优化生成模型训练
- 在MNIST变体上实现更快采样且样本质量更优
- 适合关注高质量结构化数据生成的研究者
我们提出隐变量非线性去噪得分匹配（LNDSM），一种新型得分生成模型训练目标，将非线性前向动态与基于变分自编码器（VAE）的隐变量得分生成模型（latent SGM）框架相结合。通过欧拉-马鲁亚玛方案诱导的近似高斯转移，重构交叉熵项。为保证数值稳定性，识别并移除了两个在小时间步下均值为零但方差发散的项。在多种MNIST数据集变体上的实验表明，该方法实现了更快的生成速度，并更好地学习了内在结构化分布。相较于基准的结构无关隐变量SGM，LNDSM在所有测试中均表现出更优的样本质量和多样性。
原文摘要 · Abstract (English)
We present latent nonlinear denoising score matching (LNDSM), a novel training objective for score-based generative models that integrates nonlinear forward dynamics with the VAE-based latent SGM framework. This combination is achieved by reformulating the cross-entropy term using the approximate Gaussian transition induced by the Euler-Maruyama scheme. To ensure numerical stability, we identify and remove two zero-mean but variance exploding terms arising from small time steps. Experiments on variants of the MNIST dataset demonstrate that the proposed method achieves faster synthesis and enhanced learning of inherently structured distributions. Compared to benchmark structure-agnostic latent SGMs, LNDSM consistently attains superior sample quality and variability.
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。