用物理理论优化神经网络权重分布，提升模型稳定性。
DFReg: A Physics-Inspired Framework for Global Weight Distribution Regularization in Neural Networks
- 借鉴密度泛函理论设计全局权重正则化方法
- 使权重分布更平滑多样，无需修改网络结构
- 适合追求模型鲁棒性的研究人员
我们提出DFReg，一种受物理理论启发的深度神经网络正则化方法，作用于权重的全局分布。该方法基于密度泛函理论（DFT），通过引入泛函惩罚项，促使权重配置更加平滑、多样且分布均匀。与传统的Dropout或L2正则化不同，DFReg在不改变网络架构或引入随机扰动的前提下，施加全局结构正则性，从而增强模型的稳定性和泛化能力。
原文摘要 · Abstract (English)
We introduce DFReg, a physics-inspired regularization method for deep neural networks that operates on the global distribution of weights. Drawing from Density Functional Theory (DFT), DFReg applies a functional penalty to encourage smooth, diverse, and well-distributed weight configurations. Unlike traditional techniques such as Dropout or L2 decay, DFReg imposes global structural regularity without architectural changes or stochastic perturbations.
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。