Combinatorial Online Prediction via Metarounding.
ALGORITHMIC LEARNING THEORY (ALT 2013)(2013)
摘要
We consider online prediction problems of combinatorial concepts. Examples of such concepts include s-t paths, permutations, truth assignments, set covers, and so on. The goal of the online prediction algorithm is to compete with the best fixed combinatorial concept in hindsight. A generic approach to this problem is to design an online prediction algorithm using the corresponding offline (approximation) algorithm as an oracle. The current state-of-the art method, however, is not efficient enough. In this paper we propose a more efficient online prediction algorithm when the offline approximation algorithm has a guarantee of the integrality gap.
更多查看译文
关键词
Approximation Ratio, Truth Assignment, Rank Aggregation, Ellipsoid Method, Combinatorial Concept
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要