论文标题
在逻辑模型中的Alpha-Loss景观上
On the alpha-loss Landscape in the Logistic Model
论文作者
论文摘要
We analyze the optimization landscape of a recently introduced tunable class of loss functions called $α$-loss, $α\in (0,\infty]$, in the logistic model. This family encapsulates the exponential loss ($α= 1/2$), the log-loss ($α= 1$), and the 0-1 loss ($α= \infty$) and contains compelling properties that enable the practitioner to在与新兴的学习方法相关的许多工作条件中，我们研究了$α$ - 损失的优化景观，使用$α$的$α$使用从严格的Quasi-convex函数进行研究以外的几何技术来解释这些结果。
We analyze the optimization landscape of a recently introduced tunable class of loss functions called $α$-loss, $α\in (0,\infty]$, in the logistic model. This family encapsulates the exponential loss ($α= 1/2$), the log-loss ($α= 1$), and the 0-1 loss ($α= \infty$) and contains compelling properties that enable the practitioner to discern among a host of operating conditions relevant to emerging learning methods. Specifically, we study the evolution of the optimization landscape of $α$-loss with respect to $α$ using tools drawn from the study of strictly-locally-quasi-convex functions in addition to geometric techniques. We interpret these results in terms of optimization complexity via normalized gradient descent.
