BriefGPT.xyz
Dec, 2012
带痕范数正则化的多任务学习的超额风险界
Excess risk bounds for multitask learning with trace norm regularization
HTML
PDF
Andreas Maurer, Massimiliano Pontil
TL;DR
通过轨迹规范化正则化方法，可以在多任务学习中提高精度和性能，并给出过量风险界，并且独立于输入空间维度，同时考虑到数据分布的属性以及任务数和每个任务的示例数。
Abstract
trace norm regularization
is a popular method of
multitask learning
. We give
excess risk bounds
with explicit dependence on the number of
→