arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1506.03271cs.LGstat.ML
收藏

不再探索:改进非随机土匪的高概率后悔界限

Explore no more: Improved high-probability regret bounds for non-stochastic bandits

Pompeu Fabra University(庞培法布拉大学);INRIA Lille – Nord Europe(法国国家信息与自动化研究所里尔-北欧分所)

Gergely Neu

摘要:

本文研究了非随机多臂强盗问题中的后悔最小化问题,重点研究了高概率下的性能保证。这样的结果在文献中是相当罕见的,因为证明它们需要大量的技术努力和对标准的重大修改,更直观的算法,只有保证保持期望。这些修改之一是强制学习器在$T$轮上从均匀分布中至少$Ω(\sqrt{T})$次采样臂,如果许多臂是次优的,则这会对性能产生不利影响。虽然人们普遍认为,这个属性是必不可少的证明高概率的遗憾界,我们在本文中表明,它是可能实现这样强的结果,没有这种不理想的探索组件。我们的结果依赖于一个简单而直观的损失估计策略,称为隐式探索(IX),允许一个非常干净的分析。为了证明我们的技术的灵活性,我们得到了几个改进的高概率界的各种扩展的标准多臂强盗框架。最后,我们进行了一个简单的实验,说明了我们的隐式探索技术的鲁棒性。

英文摘要:

This work addresses the problem of regret minimization in non-stochastic multi-armed bandit problems, focusing on performance guarantees that hold with high probability. Such results are rather scarce in the literature since proving them requires a large deal of technical effort and significant modifications to the standard, more intuitive algorithms that come only with guarantees that hold on expectation. One of these modifications is forcing the learner to sample arms from the uniform distribution at least $Ω(\sqrt{T})$ times over $T$ rounds, which can adversely affect performance if many of the arms are suboptimal. While it is widely conjectured that this property is essential for proving high-probability regret bounds, we show in this paper that it is possible to achieve such strong results without this undesirable exploration component. Our result relies on a simple and intuitive loss-estimation strategy called Implicit eXploration (IX) that allows a remarkably clean analysis. To demonstrate the flexibility of our technique, we derive several improved high-probability bounds for various extensions of the standard multi-armed bandit framework. Finally, we conduct a simple experiment that illustrates the robustness of our implicit exploration technique.

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。

↑