We explore the maximum likelihood degree of a homogeneous polynomial $F$ on a projective variety $X$, $\mathrm{MLD}_X(F)$, which generalizes the concept of Gaussian maximum likelihood degree. We show that $\mathrm{MLD}_X(F)$ is equal to the count of critical points of a rational function on $X$, and give different geometric characterizations of it via topological Euler characteristic, dual varieties, and Chern classes.
翻译:我们探索了单一多角美元(F)的最大可能性,其投影种类为X美元,$\mathrm{MLD*X(F)美元,它概括了高斯最大可能性程度的概念。我们显示,$\mathrm{MLD*X(F)美元等于以X美元计算一个合理函数的临界点,并通过表层脉冲特征、双重品种和切尔氏等级对它进行不同的几何定性。