一个数学分离超平面定理及其应用
An Algorithmic Separating Hyperplane Theorem and Its Applications
摘要:
本文首先证明了一个新的分离超平面定理,它刻画了欧氏空间的一对紧凸子集$K, K'$何时相交,何时不相交。这个定理不同于经典的分离定理。它推广了{ \it距离对偶}在我们早期的工作中证明的有限点集的凸壳中的一个区别点的成员资格。其次,利用该定理,我们发展了一个基本上广义的和更强的版本的{ \it三角形算法}在以前的工作中介绍,以执行以下三个任务中的任何一个:(1)计算一对$(p,p') \in K \times K'$,其中要么欧几里德距离$d(p,p')$是在一个规定的公差,或正交平分超平面的线段$pp'$分开的两个集合;(2)当$K$和$K'$不相交时,计算$(p,p') \in K \times K'$,使得$d(p,p')$近似于$d(K,K')$在规定的容差内;(3)当$K$和$K'$不相交时,计算一对平行支撑超平面$H,H'$,使得$d(H,H')$在最优裕度的规定容差内。每次迭代的最坏情况复杂度是在$K$或$K'$上求解线性目标。由此产生的算法是一个完全多项式时间的近似计划,当$K$和$K'$是凸包的有限点集,或相交的有限数量的半空间等重要的特殊情况。这些结果在机器学习、统计、线性、二次和凸规划等领域有着广泛的理论和实际应用。特别是,在另一篇文章中,我们报告了三角形算法和SMO解决硬利润问题的比较。在未来的工作中,我们将应用扩展到组合和NP完全问题。
英文摘要:
We first prove a new separating hyperplane theorem characterizing when a pair of compact convex subsets $K, K'$ of the Euclidean space intersect, and when they are disjoint. The theorem is distinct from classical separation theorems. It generalizes the {\it distance duality} proved in our earlier work for testing the membership of a distinguished point in the convex hull of a finite point set. Next by utilizing the theorem, we develop a substantially generalized and stronger version of the {\it Triangle Algorithm} introduced in the previous work to perform any of the following three tasks: (1) To compute a pair $(p,p') \in K \times K'$, where either the Euclidean distance $d(p,p')$ is to within a prescribed tolerance, or the orthogonal bisecting hyperplane of the line segment $pp'$ separates the two sets; (2) When $K$ and $K'$ are disjoint, to compute $(p,p') \in K \times K'$ so that $d(p,p')$ approximates $d(K,K')$ to within a prescribed tolerance; (3) When $K$ and $K'$ are disjoint, to compute a pair of parallel supporting hyperplanes $H,H'$ so that $d(H,H')$ is to within a prescribed tolerance of the optimal margin. The worst-case complexity of each iteration is solving a linear objective over $K$ or $K'$. The resulting algorithm is a fully polynomial-time approximation scheme for such important special cases as when $K$ and $K'$ are convex hulls of finite points sets, or the intersection of a finite number of halfspaces. The results find many theoretical and practical applications, such as in machine learning, statistics, linear, quadratic and convex programming. In particular, in a separate article we report on a comparison of the Triangle Algorithm and SMO for solving the hard margin problem. In future work we extend the applications to combinatorial and NP-complete problems.
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。