用贝叶斯推断重看扩散模型，提升生成质量。
Generative Modeling with Bayesian Sample Inference
- 将采样过程视为迭代后验推断，把样本当未知变量处理。
- 在ImageNet32/64上样本质量优于BFN和变分扩散模型。
- 理论统一了贝叶斯流网络与扩散模型，适合研究生成机制者阅读。
我们从迭代高斯后验推断的角度，提出一种扩散类生成建模的新视角。将生成样本视为未知变量，以贝叶斯概率语言描述采样过程：每一步中，模型基于当前信念预测样本，并据此计算新的后验信念。基于此框架，我们提出生成模型贝叶斯样本推断（BSI）。除严格的理论分析外，我们证明该视角包含贝叶斯流网络（BFNs），且BSI与BFNs代表初始信念状态上各向同性超先验的两个极端。实验表明，在ImageNet32和ImageNet64上，BSI在样本质量上优于BFN和变分扩散模型，同时在两个数据集上对数似然相当。
原文摘要 · Abstract (English)
We present a novel view of diffusion-like generative modeling from the perspective of iterative Gaussian posterior inference. By treating the generated sample as an unknown variable, we formulate the sampling process in the language of Bayesian probability: at each step, a model predicts the unknown sample from our current belief state and we compute a posterior belief from that prediction. Based on this formulation, we propose the generative model Bayesian Sample Inference (BSI). In addition to a rigorous theoretical analysis, we show that our perspective includes Bayesian Flow Networks (BFNs) and that BSI and BFNs represent the two opposite ends of a range of isotropic hyper-priors over the initial belief state. In our experiments, we demonstrate that BSI improves sample quality over both BFNs and the closely related Variational Diffusion Models on ImageNet32 and ImageNet64, while achieving equivalent log-likelihoods on both datasets.
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。