arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.03391cs.PL
收藏

概率规划的参数

Paradoxes of Probabilistic Programming

Jules Jacobs

摘要:

概率论程序设计语言允许程序员将表示统计和机器学习模型的条件概率分布写为使用观察语句的程序。这些程序通过在每个观察语句处累积似然性来运行,并使用似然性来引导随机选择并使用诸如重要性采样或MCMC之类的推理算法来权衡结果。我们认为,天真的似然积累没有得到理想的语义,并导致悖论时,观察语句是用来测量零事件的条件,特别是当观察语句有条件地执行随机数据。我们发现,如果我们明确地将零测量事件建模为正测量事件的极限,则悖论消失,并且我们可以通过累积无穷小概率而不是概率密度来执行这些类型的概率程序。我们的扩展改进了概率程序设计语言作为一个可执行符号的概率分布,使其更好的行为和更有表现力,通过允许程序员明确的限制是打算条件时,测量零的事件。

英文摘要:

Probabilistic programming languages allow programmers to write down conditional probability distributions that represent statistical and machine learning models as programs that use observe statements. These programs are run by accumulating likelihood at each observe statement, and using the likelihood to steer random choices and weigh results with inference algorithms such as importance sampling or MCMC. We argue that naive likelihood accumulation does not give desirable semantics and leads to paradoxes when an observe statement is used to condition on a measure-zero event, particularly when the observe statement is executed conditionally on random data. We show that the paradoxes disappear if we explicitly model measure-zero events as a limit of positive measure events, and that we can execute these type of probabilistic programs by accumulating infinitesimal probabilities rather than probability densities. Our extension improves probabilistic programming languages as an executable notation for probability distributions by making it more well-behaved and more expressive, by allowing the programmer to be explicit about which limit is intended when conditioning on an event of measure zero.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑