研究概率计算图的离散误差，给出无假设下的精确误差界。
Distributional Computational Graphs: Error Bounds
- 用概率分布代替数值输入构建计算图，分析其离散化误差。
- 在Wasserstein-1距离下建立非渐近误差上界，不依赖图结构。
- 适合关注概率推理、不确定性建模的研究者参考。
我们研究一种通用的概率计算图框架：输入为概率分布而非确定数值的计算图。分析当使用连续概率分布的有限近似来评估这些图时产生的离散化误差。这种近似可能是将连续实值分布离散化表示的结果，或从样本构造的经验分布（也可能是另一个概率计算图的输出）。我们在不施加计算图结构假设的前提下，基于Wasserstein-1距离建立了非渐近误差界。
原文摘要 · Abstract (English)
We study a general framework of distributional computational graphs: computational graphs whose inputs are probability distributions rather than point values. We analyze the discretization error that arises when these graphs are evaluated using finite approximations of continuous probability distributions. Such an approximation might be the result of representing a continuous real-valued distribution using a discrete representation or from constructing an empirical distribution from samples (or might be the output of another distributional computational graph). We establish non-asymptotic error bounds in terms of the Wasserstein-1 distance, without imposing structural assumptions on the computational graph.
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。