arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.06990cs.LGcs.PL
收藏

基于搜索梯度的引导式草图程序归纳

Guided Sketch-Based Program Induction by Search Gradients

Toronto Metropolitan University(多伦多都会大学)

Ahmad Ayaz Amin

AI总结:

针对传统程序归纳难以适应多任务的问题,提出利用进化策略通过搜索梯度学习参数化程序的框架,允许注入特定任务代码至程序草图并实现端到端梯度优化加速学习。

摘要:

许多任务可以使用机器学习技术轻松解决。然而,有些任务无法用统计模型直接解决,而需要采用符号方法。程序归纳是解决此类任务的方法之一,它通过训练来捕获可解释且可泛化的算法。然而,当代的程序归纳方法不够成熟,难以直接应用于各种类型的任务,因为它们往往被构建为单一的、包罗万象的模型,通常由神经网络参数化。为了使程序归纳成为适用于多种场景的可行解决方案,我们提出了一个框架,利用进化策略通过搜索梯度来学习参数化程序。这种表述有别于传统的程序归纳,因为它允许程序员将特定任务的代码注入程序的“草图(sketch)”中,同时还能通过端到端的基于梯度的优化来享受加速学习的好处。

英文摘要:

Many tasks can be easily solved using machine learning techniques. However, some tasks cannot readily be solved using statistical models, requiring a symbolic approach instead. Program induction is one of the ways that such tasks can be solved by means of capturing an interpretable and generalizable algorithm through training. However, contemporary approaches to program induction are not sophisticated enough to readily be applied to various types of tasks as they tend to be formulated as a single, all-encompassing model, usually parameterized by neural networks. In an attempt to make program induction a viable solution for many scenarios, we propose a framework for learning parameterized programs via search gradients using evolution strategies. This formulation departs from traditional program induction as it allows for the programmer to impart task-specific code to the program 'sketch', while also enjoying the benefits of accelerated learning through end-to-end gradient-based optimization.

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。

↑