BriefGPT.xyz
Oct, 2021
核化异构风险最小化
Kernelized Heterogeneous Risk Minimization
HTML
PDF
Jiashuo Liu, Zheyuan Hu, Peng Cui, Bo Li, Zheyan Shen
TL;DR
本文介绍了一种基于核化的异构风险最小化算法，实现了潜在特性探索和不变学习，并通过指定不变梯度方向向原始神经网络传递反馈。我们从理论和实践两方面证明了我们的算法的有效性。
Abstract
The ability to generalize under
distributional shifts
is essential to reliable machine learning, while models optimized with empirical risk minimization usually fail on non-$i.i.d$ testing data. Recently,
invariant lear
→