PulseAugur
实时 13:56:54
English(EN) Deep Variational Inference Symbolic Regression

新AI方法增强符号回归以促进科学发现

研究人员开发了新的符号回归方法,这是一种用于从数据中发现数学表达式的技术。一种方法是程序化上下文增强(Programmatic Context Augmentation),它通过允许基于代码与数据集的交互来提取超越简单评估指标的更丰富信号,从而增强了基于LLM的进化搜索。另一种方法是深度变分推理符号回归(DVISR),它通过引入变分贝叶斯原理来推断候选表达式及其常数的后验分布,从而量化不确定性,扩展了深度符号回归。第三篇论文提出了一种用于生成控制方程符号表达式的深度神经网络架构,将深度学习的灵活性与符号化解决方案的可解释性相结合。 AI

影响 符号回归的这些进步可以通过实现更具可解释性和准确性的数据方程生成来加速科学发现。

排序理由 多篇arXiv论文提出了使用LLM和深度学习的符号回归技术的新研究。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →

新AI方法增强符号回归以促进科学发现

报道来源 [4]

  1. arXiv cs.AI TIER_1 English(EN) · Hao Liu, Xiao-Wen Yang, Atharva Sehgal, Yixin Wang, Lan-Zhe Guo, Yu-Feng Li, Yisong Yue ·

    Programmatic Context Augmentation for LLM-based Symbolic Regression

    arXiv:2605.03101v1 Announce Type: new Abstract: Symbolic regression (SR), the task of discovering mathematical expressions that best describe a given dataset, remains a fundamental challenge in scientific discovery. Traditional approaches, primarily based on genetic algorithms an…

  2. arXiv cs.LG TIER_1 English(EN) · James Butterworth, Gevik Grigorian, Alejandro DiazDelaO ·

    Deep Variational Inference Symbolic Regression

    arXiv:2605.01067v1 Announce Type: new Abstract: Symbolic regression discovers explicit, interpretable equations without assuming a functional form in advance. A Bayesian approach strengthens this through probability distributions over candidate expressions, thus quantifying uncer…

  3. arXiv stat.ML TIER_1 English(EN) · Nibodh Boddupalli, Timothy Matchen, Jeff Moehlis ·

    Symbolic Regression via Neural Networks

    arXiv:2605.04337v1 Announce Type: cross Abstract: Identifying governing equations for a dynamical system is a topic of critical interest across an array of disciplines, from mathematics to engineering to biology. Machine learning -- specifically deep learning -- techniques have s…

  4. arXiv stat.ML TIER_1 English(EN) · Jeff Moehlis ·

    Symbolic Regression via Neural Networks

    Identifying governing equations for a dynamical system is a topic of critical interest across an array of disciplines, from mathematics to engineering to biology. Machine learning -- specifically deep learning -- techniques have shown their capabilities in approximating dynamics …