几何不变性和等变性的检验
Testing for Geometric Invariance and Equivariance
摘要:
不变和等变模型包含了待估计对象的对称性(此处为非参数回归函数$f : \mathcal{X} \rightarrow \mathbb{R}$)。这些模型表现更好(相对于$L^2$损失),并越来越多地在实践中使用,但遇到的问题时,对称性是错误的假设。在本文中,我们提出了一个框架测试的$G$ -等方差的任何半群$G$。当对称性不是先验已知的时,这将给予使用这样的模型的信心。这些测试独立于模型,计算速度快,因此可以在模型拟合之前轻松使用,以测试其有效性。
英文摘要:
Invariant and equivariant models incorporate the symmetry of an object to be estimated (here non-parametric regression functions $f : \mathcal{X} \rightarrow \mathbb{R}$). These models perform better (with respect to $L^2$ loss) and are increasingly being used in practice, but encounter problems when the symmetry is falsely assumed. In this paper we present a framework for testing for $G$-equivariance for any semi-group $G$. This will give confidence to the use of such models when the symmetry is not known a priori. These tests are independent of the model and are computationally quick, so can be easily used before model fitting to test their validity.
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。