Forward-Value Discretization：无需高阶近似的随机扩散采样加速方法
Forward-Value Discretization: Faster Stochastic Diffusion Sampling Without High-Order Approximation
扩散模型随机采样比确定性采样慢的问题，这篇论文给出了理论解释和免训练解法：F-DDPM 复用历史预测和噪声构造前瞻点，同 NFE 下 FID 更低，只多花 1.5 倍 NFE 就接近确定性采样质量。做生成模型部署或采样器研究的工程师可以直接看开源代码。
论文提出 forward-value discretization，一个免训练的扩散采样加速框架，并基于它开发了 F-DPMSolver 和 F-DDPM 两个采样器。
作者先给出匹配的上下界证明：即使分数函数完全准确，随机采样器使用高阶近似仍只有一阶收敛，因此提高近似阶数一般无法提升随机采样的收敛速度。F-DDPM 的做法是在由先前预测构造的前瞻点上评估模型，同时复用上一步的模型预测和上一步注入的噪声，并针对后续噪声注入进行调整，每次迭代只需一次模型评估。
在 CIFAR-10、ImageNet、FFHQ 和 LSUN 四个数据集上，F-DDPM 在相同 NFE 预算下 FID 一致低于被评测的随机采样基线；当 NFE 达到确定性基线的 1.
5 倍时，样本质量已具竞争力，缩小了随机采样与确定性采样之间的实际效率差距。代码已在 GitHub 开源。
Forward-Value Discretization: Faster Stochastic Diffusion Sampling Without High-Order Approximation
Stochastic diffusion samplers often require substantially more neural function evaluations (NFEs) than deterministic samplers to achieve comparable sample quality. Although higher-order discretization accelerates deterministic sampling, its benefits for stochastic sampling remains unclear. We establish matching upper and worst-case lower bounds showing that stochastic samplers with higher-order approximations remain first-order convergent, even with exact score functions. Thus, increasing the approximation order does not generally improve the convergence order. Motivated by this limitation, we introduce forward-value discretization, a training-free framework that evaluates the data/noise prediction model at a lookahead estimate constructed from previous predictions. For deterministic sampling, the resulting Forward DPMSolver (F-DPMSolver), improves sample quality at low NFE budgets through its DDIM-based variant, despite remaining first-order convergent. For stochastic sampling, we develop Forward DDPM (F-DDPM), which evaluates the model at a cleaner lookahead point adjusted for subsequent noise injection. This estimate reuses both the previous model prediction and the previously injected noise. Both variants admit first-order convergence guarantees with one model evaluation per iteration. Across CIFAR-10, ImageNet, FFHQ, and LSUN, F-DDPM consistently achieves lower FID than the evaluated stochastic baselines at matched NFE budgets. With 1.5 times as many NFEs as deterministic baselines, it achieves competitive sample quality, narrowing the practical efficiency gap between stochastic and deterministic sampling. Code is available at https://github.com/Na-Li66/F-DDPM.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：F-DDPM、DPMSolver、扩散模型、采样加速，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.AI」（@Yuchen Jiao, Na Li, Changxiao Cai, Yuting Wei, Gen Li），经 AITOP 多维评分管线结构化提炼。