论文阅读 [TPAMI-2022] Average Top-k Aggregate Loss for Supervised Learning

论文阅读 [TPAMI-2022] Average Top-k Aggregate Loss for Supervised Learning

论文搜索(studyai.com)

搜索论文: Average Top-k Aggregate Loss for Supervised Learning

搜索论文: http://www.studyai.com/search/whole-site/?q=Average+Top-k+Aggregate+Loss+for+Supervised+Learning

关键字(Keywords)

Aggregates; Training; Training data; Supervised learning; Data models; Loss measurement; Task analysis; Aggregate loss; average top- $k$ k loss; supervised learning; learning theory

机器学习; 机器视觉

监督学习; 图像分类; SVM

摘要(Abstract)

In this work, we introduce the average top-$k$k (${\mathrm{A}\mathrm{T}}_k$ AT k) loss, which is the average over the $k$k largest individual losses over a training data, as a new aggregate loss for supervised learning.

在本文中，我们引入了平均top-$k$k（$\mathrm{A}\mathrm{T}k$AT k）损失，它是在训练数据上前$k$个最大个体损失的平均值，作为监督学习的一个新的平均损失。

We show that the ${\mathrm{A}\mathrm{T}}_k$ AT k loss is a natural generalization of the two widely used aggregate losses, namely the average loss and the maximum loss.

我们展示了 ${\mathrm{A}\mathrm{T}}_k$ AT k 损失是另外两种更广泛使用的损失(即平均损失和最大损失)的一个自然推广。

Yet, the ${\mathrm{A}\mathrm{T}}_k$ AT k loss can better adapt to different data distributions because of the extra flexibility provided by the different choices of $k$k.

然而，$\mathrm{A}\mathrm{T}k$AT k 损失可以更好地适应不同的数据分布，因为$k$k的不同选择提供了额外的灵活性。

Furthermore, it remains a convex function over all individual losses and can be combined with different types of individual loss without significant increase in computation.

此外，它仍然是所有单个损失的凸函数，可以与不同类型的单个损失结合使用，而不会显著增加计算量。

We then provide interpretations of the ${\mathrm{A}\mathrm{T}}_k$ AT k loss from the perspective of the modification of individual loss and robustness to training data distributions.

然后，我们从个体损失的修正和训练数据分布的稳健性的角度解释了$\mathrm{A}\mathrm{T}k$AT k损失。

We further study the classification calibration of the ${\mathrm{A}\mathrm{T}}_k$ AT k loss and the error bounds of ${\mathrm{A}\mathrm{T}}_k$ AT k-SVM model.

我们进一步研究了 ${\mathrm{A}\mathrm{T}}_k$ AT k 损失的分类校正和${\mathrm{A}\mathrm{T}}_k$ AT k-SVM模型的误差界。

We demonstrate the applicability of minimum average top-$k$k learning for supervised learning problems including binary/multi-class classification and regression, using experiments on both synthetic and real datasets…

我们通过在合成数据集和真实数据集上的实验，证明了最小平均top-$k$k学习对监督学习问题的适用性，包括二元/多类分类和回归。

作者(Authors)

[‘Siwei Lyu’, ‘Yanbo Fan’, ‘Yiming Ying’, ‘Bao-Gang Hu’]