We consider the online multiclass linear classification under the bandit feedback setting. Beygelzimer, P\'{a}l, Sz\"{o}r\'{e}nyi, Thiruvenkatachari, Wei, and Zhang [ICML'19] considered two notions of linear separability, weak and strong linear separability. When examples are strongly linearly separable with margin $\gamma$, they presented an algorithm based on Multiclass Perceptron with mistake bound $O(K/\gamma^2)$, where $K$ is the number of classes. They employed rational kernel to deal with examples under the weakly linearly separable condition, and obtained the mistake bound of $\min(K\cdot 2^{\tilde{O}(K\log^2(1/\gamma))},K\cdot 2^{\tilde{O}(\sqrt{1/\gamma}\log K)})$. In this paper, we refine the notion of weak linear separability to support the notion of class grouping, called group weak linear separable condition. This situation may arise from the fact that class structures contain inherent grouping. We show that under this condition, we can also use the rational kernel and obtain the mistake bound of $K\cdot 2^{\tilde{O}(\sqrt{1/\gamma}\log L)})$, where $L\leq K$ represents the number of groups.
翻译:我们考虑在土匪反馈设置下在线多级线性分类 。 Beygelzimer, P\ {a}l, Sz\\\\\\\\\{{{e}nyi, Thiruvenkataari, Wei, and Zhang[ICML'19] 考虑了线性分离、弱和强线性分离的两个概念。当示例以差值$\gamma{O} 明显线性分离时,它们提出了一个基于多级 Percepron 的算法,其中$O( K/\\\ gamma}, $K$( K/\\ gamma} 代表$( K$), 其中, $是K$( K) 的合理内核, 他们用理性内核内核( K) 的内核结构, 我们也可以从这个类的内核( ) 类结构中, 显示内核( ) 内核) 的内核状态 。