Sampling based on score diffusions has led to striking empirical results, and has attracted considerable attention from various research communities. It depends on availability of (approximate) Stein score functions for various levels of additive noise. We describe and analyze a modular scheme that reduces score-based sampling to solving a short sequence of ``nice'' sampling problems, for which high-accuracy samplers are known. We show how to design forward trajectories such that both (a) the terminal distribution, and (b) each of the backward conditional distribution is defined by a strongly log concave (SLC) distribution. This modular reduction allows us to exploit \emph{any} SLC sampling algorithm in order to traverse the backwards path, and we establish novel guarantees with short proofs for both uni-modal and multi-modal densities. The use of high-accuracy routines yields $\varepsilon$-accurate answers, in either KL or Wasserstein distances, with polynomial dependence on $\log(1/\varepsilon)$ and $\sqrt{d}$ dependence on the dimension.
翻译:基于分数扩散的采样已取得显著的实证成果,并引起了多个研究领域的广泛关注。该方法依赖于不同加性噪声水平下(近似)斯坦分数函数的可用性。我们描述并分析了一种模块化方案,该方案将基于分数的采样简化为求解一系列短序列的“理想”采样问题,而针对此类问题已有高精度采样器被提出。我们展示了如何设计前向轨迹,使得(a)终端分布及(b)每个反向条件分布均由强对数凹分布定义。这种模块化归约使我们能够利用任意强对数凹采样算法来遍历反向路径,并为单峰与多峰密度建立了具有简洁证明的新理论保证。通过采用高精度采样例程,可在KL散度或Wasserstein距离下获得$\varepsilon$精度的解,其对$\log(1/\varepsilon)$具有多项式依赖关系,对维度$d$具有$\sqrt{d}$依赖关系。