TL;DR本文对基于对比学习的非线性独立分量分析进行了有限样本识别能力分析,该分析框架聚合了 GCL loss 函数的特性,统计概括分析和数值微分,并考虑到学习函数的逼近误差。
Abstract
nonlinear independent component analysis (nICA) aims at recovering
statistically independent latent components that are mixed by unknown nonlinear
functions. Central to nICA is the identifiability of the latent c