Label Smoothing (LS) improves model generalization through penalizing models
from generating overconfident output distributions. For each training sample
the LS strategy smooths the one-hot encoded training signal by distributing its
distribution mass over the non-ground truth classes. We extend this technique
by considering example pairs, coined PLS. PLS first creates midpoint samples by
averaging random sample pairs and then learns a smoothing distribution during
training for each of these midpoint samples, resulting in midpoints with high
uncertainty labels for training. We empirically show that PLS significantly
outperforms LS, achieving up to 30% of relative classification error reduction.
We also visualize that PLS produces very low winning softmax scores for both in
and out of distribution samples.

本文介绍了标签平滑（LS）和 example pairs 平滑（PLS）两种方法，其中 PLS 方法较 LS 方法在模型泛化和分类错误率降低等方面表现更优，通过平滑处理来生成高不确定性标签的样本用于训练，实验结果证明了 PLS 方法的有效性。

中点正则化：从高度不确定性训练到保守分类

Midpoint Regularization: from High Uncertainty Training to Conservative  Classification

We study search problems that can be solved by performing Gradient Descent on
a bounded convex polytopal domain and show that this class is equal to the
intersection of two well-known classes: PPAD and PLS. As our main underlying
technical contribution, we show that computing a Karush-Kuhn-Tucker (KKT) point
of a continuously differentiable function over the domain $[0,1]^2$ is PPAD
$\cap$ PLS-complete. This is the first non-artificial problem to be shown
complete for this class. Our results also imply that the class CLS (Continuous
Local Search) - which was defined by Daskalakis and Papadimitriou as a more
"natural" counterpart to PPAD $\cap$ PLS and contains many interesting problems
- is itself equal to PPAD $\cap$ PLS.

该论文研究了在有界凸多面体域上通过梯度下降解决的搜索问题，并表明该类等于两个众所周知的类的交集：PPAD 和 PLS。同时证明了在区间 [0,1] x [0,1] 上计算连续可微函数的 Karush-Kuhn-Tucker（KKT）点是 PPAD 和 PLS 完全的第一个非人工问题。该研究结果还表明，Daskalakis 和 Papadimitriou 定义的 CLS 类（连续局部搜索） - 它是 PPAD 和 PLS 的更 “自然” 对应物，其中包含许多有趣的问题 - 本身等于 PPAD 和 PLS。