论文标题
Toprank+：Toprank算法的改进
TopRank+: A Refinement of TopRank Algorithm
论文作者
论文摘要
在线学习排名是机器学习中的核心问题。在Lattimore等。 （2018），一种基于拓扑排序提出了一种新颖的在线学习算法。在论文中，他们提供了算法中的一组自称不平等（a）作为迭代标准，并且（b）为累积遗憾提供了上限，这是算法性能的度量。在这项工作中，我们利用了某些隐式函数的混合物和渐近扩展方法为不平等现象提供更紧密的，迭代的log样边界，并因此改善了算法本身及其性能估计。
Online learning to rank is a core problem in machine learning. In Lattimore et al. (2018), a novel online learning algorithm was proposed based on topological sorting. In the paper they provided a set of self-normalized inequalities (a) in the algorithm as a criterion in iterations and (b) to provide an upper bound for cumulative regret, which is a measure of algorithm performance. In this work, we utilized method of mixtures and asymptotic expansions of certain implicit function to provide a tighter, iterated-log-like boundary for the inequalities, and as a consequence improve both the algorithm itself as well as its performance estimation.
