Learning Programs: A Hierarchical Bayesian Approach
Learning Programs: A Hierarchical Bayesian Approach
复制标题
学习计划：分层贝叶斯方法
DOI：
--
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
D. Klein
中科院分区：
文献类型：
--
作者：
P. Liang;Michael I. Jordan;D. Klein
我们对针对多个相关任务的学习程序感兴趣，每个任务仅提供几个训练示例。由于单个任务的程序由其数据决定不足，因此我们在跨多个任务共享统计强度的程序上引入了非参数分层贝叶斯先验。关键的挑战是参数化这种多任务共享。为此，我们引入了一种基于组合逻辑的新程序表示，并提供了一种 MCMC 算法，该算法可以对此表示执行安全的程序转换，以揭示共享的程序间子结构。
We are interested in learning programs for multiple related tasks given only a few training examples per task. Since the program for a single task is underdetermined by its data, we introduce a nonparametric hierarchical Bayesian prior over programs which shares statistical strength across multiple tasks. The key challenge is to parametrize this multi-task sharing. For this, we introduce a new representation of programs based on combinatory logic and provide an MCMC algorithm that can perform safe program transformations on this representation to reveal shared inter-program substructures.