GenEFT：通过有效理论理解模型泛化的静力学与动力学
GenEFT: Understanding Statics and Dynamics of Model Generalization via Effective Theory
AI总结：
本研究提出GenEFT有效理论框架，结合图学习实验揭示神经网络泛化的静力学与动力学规律，解释泛化相变现象，为衔接机器学习理论与实践提供物理学启发的新路径。
摘要：
我们提出GenEFT：一种用于揭示神经网络泛化静力学与动力学规律的有效理论框架，并以图学习示例对其进行阐释。我们首先研究了随数据规模增大的泛化相变，将实验结果与基于信息论的近似方法进行对比，发现泛化存在于一个“金发姑娘区”，即解码器既不过弱也不过强的区间。随后我们提出一种表征学习动力学的有效理论，将潜空间表征建模为相互作用粒子（响应子），发现该理论能够解释实验中观测到的、扫描编码器与解码器学习率时泛化与过拟合之间的相变。这凸显了受物理学启发的有效理论在弥合机器学习理论预测与实践差距方面的作用。
英文摘要：
We present GenEFT: an effective theory framework for shedding light on the statics and dynamics of neural network generalization, and illustrate it with graph learning examples. We first investigate the generalization phase transition as data size increases, comparing experimental results with information-theory-based approximations. We find generalization in a Goldilocks zone where the decoder is neither too weak nor too powerful. We then introduce an effective theory for the dynamics of representation learning, where latent-space representations are modeled as interacting particles (repons), and find that it explains our experimentally observed phase transition between generalization and overfitting as encoder and decoder learning rates are scanned. This highlights the power of physics-inspired effective theories for bridging the gap between theoretical predictions and practice in machine learning.
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。
