arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.05744cs.LGmath.OC
收藏

在线线性优化的无标度算法

Scale-Free Algorithms for Online Linear Optimization

Yahoo Labs(雅虎实验室)

Francesco Orabona, David Pal

摘要:

我们设计的在线线性优化算法,具有最佳的遗憾,并在同一时间不需要知道任何上限或下限的损失向量的范数。我们通过尺度不变性实现对损失向量范数的自适应,即,如果损失向量序列乘以任何正常数,我们的算法会做出完全相同的决定。我们的算法适用于任何决策集,有界或无界。对于无界决策集,这些是第一个真正的在线线性优化自适应算法。

英文摘要:

We design algorithms for online linear optimization that have optimal regret and at the same time do not need to know any upper or lower bounds on the norm of the loss vectors. We achieve adaptiveness to norms of loss vectors by scale invariance, i.e., our algorithms make exactly the same decisions if the sequence of loss vectors is multiplied by any positive constant. Our algorithms work for any decision set, bounded or unbounded. For unbounded decisions sets, these are the first truly adaptive algorithms for online linear optimization.

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。

↑