提出SimpliPy加速符号回归，提升模型效率与表达式简洁性。
Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression
- 设计基于规则的简化引擎SimpliPy，速度比SymPy快100倍
- 在FastSRB上优于现有摊销方法，精度更高且表达式更简洁
- 适合需要高效、可解释模型的科学计算场景
符号回归（SR）旨在发现能准确描述数据的可解释解析表达式。摊销式符号回归虽比主流遗传编程方法更高效，但难以应对真实科学复杂度。我们发现其关键瓶颈在于缺乏快速将等价表达式归约为紧凑标准形式的能力。现有方法依赖通用计算机代数系统（如SymPy），但计算成本高，严重限制训练与推理速度。本文提出SimpliPy，一种基于规则的简化引擎，在保持相近质量的前提下实现比SymPy快100倍的性能。这使得摊销式符号回归显著提升：可扩展至更大训练集、更高效利用每表达式的词元预算，并系统性剔除测试表达式中的等价冗余。我们在Flash-ANSR框架中验证了这些优势，在FastSRB基准上表现优于摊销基线（NeSymReS、E2E），且在增加推理预算时恢复更简洁而非更复杂的表达式，精度媲美最先进的直接优化方法（PySR）。
原文摘要 · Abstract (English)
Symbolic regression (SR) aims to discover interpretable analytical expressions that accurately describe observed data. Amortized SR promises to be much more efficient than the predominant genetic programming SR methods, but currently struggles to scale to realistic scientific complexity. We find that a key obstacle is the lack of a fast reduction of equivalent expressions to a concise normalized form. Amortized SR has addressed this with general-purpose Computer Algebra Systems (CAS) like SymPy, but the high computational cost severely limits training and inference speed. We propose SimpliPy, a rule-based simplification engine achieving a 100-fold speed-up over SymPy at comparable quality. This enables substantial improvements in amortized SR, including scalability to much larger training sets, more efficient use of the per-expression token budget, and systematic training set decontamination with respect to equivalent test expressions. We demonstrate these advantages in our Flash-ANSR framework, which achieves much better accuracy than amortized baselines (NeSymReS, E2E) on the FastSRB benchmark. Moreover, it performs on par with state-of-the-art direct optimization (PySR) while recovering more concise rather than more complex expressions with increasing inference budget.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。