arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1706.01284cs.LGcs.AIcs.PL
收藏

从输入输出实例综合复杂程序

Towards Synthesizing Complex Programs from Input-Output Examples

University of California, Berkeley(加州大学伯克利分校)

Xinyun Chen, Chang Liu, Dawn Song

摘要:

近年来,已经开发了深度学习技术来提高从输入-输出示例进行程序合成的性能。尽管它取得了重大进展,但就其复杂性而言,可以通过最先进的方法合成的程序仍然是简单的。在这项工作中,我们沿着这个方向向前迈出了重要的一步,提出了一类新的具有挑战性的任务,在域中的程序合成从输入输出的例子:学习上下文无关的解析器对输入程序和他们的解析树。我们发现,这类任务比以前研究的任务更具挑战性,现有方法的测试准确率几乎为0%。我们通过开发三种新颖的技术来应对挑战,这些技术的灵感来自三种新颖的观察,这些观察揭示了使用深度学习来合成复杂程序的关键因素。首先,使用不可微机器是有效限制搜索空间的关键。因此,我们提出的方法学习神经程序操作特定于域的不可微机器。其次,递归是实现可推广性的关键。因此,我们在不可微机器的设计中引入了递归的概念。第三,强化学习是学习如何操作不可微机器的关键,但是现有的强化学习算法也很难从冷启动开始有效地训练模型。我们开发了一种新的基于两阶段强化学习的搜索算法来克服这个问题。在我们的评估中,我们表明,使用我们的新方法,神经解析程序可以学习到在比训练样本长500倍的测试输入上实现100%的测试准确率。

英文摘要:

In recent years, deep learning techniques have been developed to improve the performance of program synthesis from input-output examples. Albeit its significant progress, the programs that can be synthesized by state-of-the-art approaches are still simple in terms of their complexity. In this work, we move a significant step forward along this direction by proposing a new class of challenging tasks in the domain of program synthesis from input-output examples: learning a context-free parser from pairs of input programs and their parse trees. We show that this class of tasks are much more challenging than previously studied tasks, and the test accuracy of existing approaches is almost 0%. We tackle the challenges by developing three novel techniques inspired by three novel observations, which reveal the key ingredients of using deep learning to synthesize a complex program. First, the use of a non-differentiable machine is the key to effectively restrict the search space. Thus our proposed approach learns a neural program operating a domain-specific non-differentiable machine. Second, recursion is the key to achieve generalizability. Thus, we bake-in the notion of recursion in the design of our non-differentiable machine. Third, reinforcement learning is the key to learn how to operate the non-differentiable machine, but it is also hard to train the model effectively with existing reinforcement learning algorithms from a cold boot. We develop a novel two-phase reinforcement learning-based search algorithm to overcome this issue. In our evaluation, we show that using our novel approach, neural parsing programs can be learned to achieve 100% test accuracy on test inputs that are 500x longer than the training samples.

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。

↑