arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1709.03093cs.LGmath.OC
收藏

基于近似算法的高效在线线性优化

Efficient Online Linear Optimization with Approximation Algorithms

Technion - Israel Institute of Technology(以色列理工学院)

Dan Garber

摘要:

我们重新审视问题的\textit{online linear optimization}的情况下,一组可行的行动是通过一个近似的线性优化预言与因子$α$乘法近似保证。这种设置是特别有趣的,因为它捕获了自然的在线扩展的研究\textit{offline}线性优化问题,这是NP难,但承认有效的近似算法。这里的目标是最小化$α$ \textit{-regret},它是\textit{online learning}中标准\textit{regret}对此设置的自然扩展。我们提出了新的算法,显着提高了甲骨文的复杂性,为充分的信息和土匪的变种的问题。主要是,对于这两种变体,我们提出了$α$ -遗憾界的$O(T^{-1/3})$,$T$是预测轮数,平均每次迭代仅使用$O(\log{T})$调用近似oracle。这些是第一个结果,以获得平均预言复杂性的$O(\log{T})$(或甚至多对数的$T$)和$α$ -遗憾界$O(T^{-c})$为一个常数$c>0$,为两个变种。

英文摘要:

We revisit the problem of \textit{online linear optimization} in case the set of feasible actions is accessible through an approximated linear optimization oracle with a factor $α$ multiplicative approximation guarantee. This setting is in particular interesting since it captures natural online extensions of well-studied \textit{offline} linear optimization problems which are NP-hard, yet admit efficient approximation algorithms. The goal here is to minimize the $α$\textit{-regret} which is the natural extension of the standard \textit{regret} in \textit{online learning} to this setting. We present new algorithms with significantly improved oracle complexity for both the full information and bandit variants of the problem. Mainly, for both variants, we present $α$-regret bounds of $O(T^{-1/3})$, were $T$ is the number of prediction rounds, using only $O(\log{T})$ calls to the approximation oracle per iteration, on average. These are the first results to obtain both average oracle complexity of $O(\log{T})$ (or even poly-logarithmic in $T$) and $α$-regret bound $O(T^{-c})$ for a constant $c>0$, for both variants.

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。

↑