BriefGPT.xyz
Nov, 2017
用游戏论p-Laplacian和半监督学习处理少标注数据
The game theoretic p-Laplacian and semi-supervised learning with few labels
HTML
PDF
Jeff Calder
TL;DR
研究了图上半监督学习中的博弈论 p-Laplacian，展示了在有限标记数据和无限未标记数据的情况下其是有限的。具体而言，我们展示了带有图上半监督学习的连续 p-Laplace 方程的连续极限是加权版本。我们还证明图 p-Laplace 方程的解近似是 Holder 连续的高概率。
Abstract
We study the game theoretic
p-laplacian
for
semi-supervised learning
on graphs, and show that it is well-posed in the limit of finite labeled data and infinite unlabeled data. In particular, we show that the cont
→