这项研究澄清了数据对称性与神经网络训练动力学之间的深层关系，对理解数据增强的理论基础有重要意义。做理论研究的机器学习学者值得关注，它可能影响你对数据增强策略的设计思路。
该研究探讨了训练数据的对称性是否会在神经网络的梯度流训练中产生守恒量。作者证明，在损失函数为解析且非多项式的一般情况下，数据对称性通常不会引入额外的运动积分。但对于均方误差（MSE）损失，数据增强有时会产生额外的守恒量。研究通过引入“可张量化网络”框架来描述这一现象，这类架构包括线性网络、多项式网络以及Lightning Attention。
Conservation Laws from Data Symmetry in Neural Networks
We explore whether intrinsic symmetries of the training data lead to conserved quantities during gradient-flow training of neural networks. Under the assumption that the loss function is analytic and non-polynomial, we prove that data symmetries generically do not induce any additional integrals of motion. For mean squared error (MSE) loss, on the other hand, there are situations in which data augmentation yields extra conserved quantities. We build a framework, utilizing \emph{tensorizable networks} to describe this phenomenon. Tensorizable networks are a family of architectures whose dependence on parameters and inputs can be separated using an intermediate representation. They include linear and polynomial networks, as well as Lightning Attention.