用于预测符号积分例程适用性的Transformers
Transformers to Predict the Applicability of Symbolic Integration Routines
AI总结:
针对计算机代数系统中符号积分方法选择的优化问题,本文训练transformer预测积分方法的适用性,其性能优于现有人工启发式规则,准确率最高提升30%、精确率最高提升70%,且推理时间可忽略,还可通过层集成梯度方法解释决策以支撑后续优化。
摘要:
符号积分是数学中的一个基础问题:本文研究如何在计算机代数系统(CAS)中利用机器学习优化该任务。我们训练了多个transformer模型,用于预测特定积分方法是否能成功执行,并将其与主流CAS中用于该任务的现有人工启发式规则(称为guards)进行对比。研究发现,transformer的性能优于这些guards,准确率最高提升30%,精确率最高提升70%。我们进一步表明,transformer的推理时间可忽略不计,说明其非常适合作为CAS中的guard集成到系统中。此外,我们使用Layer Integrated Gradients(层集成梯度)方法解释transformer的决策过程。在领域专家的指导下,该技术可以基于输入token解释部分预测结果,从而推动进一步优化。
英文摘要:
Symbolic integration is a fundamental problem in mathematics: we consider how machine learning may be used to optimise this task in a Computer Algebra System (CAS). We train transformers that predict whether a particular integration method will be successful, and compare against the existing human-made heuristics (called guards) that perform this task in a leading CAS. We find the transformer can outperform these guards, gaining up to 30% accuracy and 70% precision. We further show that the inference time of the transformer is inconsequential which shows that it is well-suited to include as a guard in a CAS. Furthermore, we use Layer Integrated Gradients to interpret the decisions that the transformer is making. If guided by a subject-matter expert, the technique can explain some of the predictions based on the input tokens, which can lead to further optimisations.
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。