arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.08797cs.LGstat.ML
收藏

通过乐观进行线性分离

Linear Separation via Optimism

College of Computing, Georgia Institute of Technology(佐治亚理工学院计算学院)

Rafael Hanashiro, Jacob Abernethy

摘要:

二进制线性分类从机器学习文献的早期就已经被探索过了。也许最经典的算法是Perceptron,其中维护用于分类示例的权重向量,并在发现不正确的示例时进行添加更新。感知器已经被彻底研究,几十年来已经提出了几个版本。关于感知器的关键理论事实是,只要存在具有一定裕度$γ> 0$的完美线性分类器,则找到这样的完美线性分离器所需的更新次数由$\frac{1}{γ^2}$限定。从未完全解决的问题是:是否存在一种算法,可以用更少的更新来实现这一点?在本文中,我们回答这一点是肯定的:我们提出了乐观感知算法,一个简单的过程,发现一个分离的超平面不超过$\frac{1}γ$更新。我们还通过实验表明,这种方法可以显着优于感知器。

英文摘要:

Binary linear classification has been explored since the very early days of the machine learning literature. Perhaps the most classical algorithm is the Perceptron, where a weight vector used to classify examples is maintained, and additive updates are made as incorrect examples are discovered. The Perceptron has been thoroughly studied and several versions have been proposed over many decades. The key theoretical fact about the Perceptron is that, so long as a perfect linear classifier exists with some margin $γ> 0$, the number of required updates to find such a perfect linear separator is bounded by $\frac{1}{γ^2}$. What has never been fully addressed is: does there exist an algorithm that can achieve this with fewer updates? In this paper we answer this in the affirmative: we propose the Optimistic Perceptron algorithm, a simple procedure that finds a separating hyperplane in no more than $\frac{1}γ$ updates. We also show experimentally that this procedure can significantly outperform Perceptron.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑