arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1706.00834cs.LG
收藏

在线动态规划

Online Dynamic Programming

Amazon(亚马逊);Google Research(谷歌研究)

Holakou Rahmanian, Manfred K. Warmuth, S. V. N. Vishwanathan

AI总结:

本文提出一种通用方法,将可动态规划求解的组合优化问题转化为在线学习问题,通过多路径编码和扩展Hedge算法,实现高效在线预测。

摘要:

我们提出了一种通用的方法,用于解决组合在线学习问题,这些问题的离线优化问题可以通过由任意最小-和(min-sum)递推关系定义的动态规划算法高效求解。示例包括二叉搜索树、矩阵链乘法、$k$-集合、背包问题、棒料切割和加权区间调度的在线学习。对于这些问题中的每一个,我们利用子问题的底层图(称为多DAG)来定义动态规划问题解的表示,通过将它们编码为路径的广义版本(称为多路径)。这些多路径将每个解编码为一系列连续的决策或组件,损失在这些决策或组件上是线性的。然后我们证明,每个问题的动态规划算法导致了在底层多DAG中学习多路径的在线算法。这些算法以简洁的形式维护多路径上的分布作为其假设。更具体地,我们将现有的用于在线最短路径问题的扩展Hedge和组件Hedge算法推广到学习多路径。此外,我们引入了一种新的且更快的组件Hedge预测技术,在我们的案例中,该技术直接从多路径上的分布中采样,绕过了将多路径上的分布分解为具有小支撑的混合分布的需要。

英文摘要:

We propose a general method for combinatorial online learning problems whose offline optimization problem can be solved efficiently via a dynamic programming algorithm defined by an arbitrary min-sum recurrence. Examples include online learning of Binary Search Trees, Matrix-Chain Multiplications, $k$-sets, Knapsacks, Rod Cuttings, and Weighted Interval Schedulings. For each of these problems we use the underlying graph of subproblems (called a multi-DAG) for defining a representation of the solutions of the dynamic programming problem by encoding them as a generalized version of paths (called multipaths). These multipaths encode each solution as a series of successive decisions or components over which the loss is linear. We then show that the dynamic programming algorithm for each problem leads to online algorithms for learning multipaths in the underlying multi-DAG. The algorithms maintain a distribution over the multipaths in a concise form as their hypothesis. More specifically we generalize the existing Expanded Hedge and Component Hedge algorithms for the online shortest path problem to learning multipaths. Additionally, we introduce a new and faster prediction technique for Component Hedge which in our case directly samples from a distribution over multipaths, bypassing the need to decompose the distribution over multipaths into a mixture with small support.

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。

↑