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 1405.4471cs.LG
收藏

具有复合损失函数的在线学习

Online Learning with Composite Loss Functions

Microsoft Research(微软研究院);University of Chicago(芝加哥大学);Technion(以色列理工学院)

Ofer Dekel, Jian Ding, Tomer Koren, Yuval Peres

摘要:

我们研究一类新的在线学习问题,其中每个在线算法的行动被分配一个对抗值,并且算法在每一步的损失是分配给其最近行动的值的已知和确定性函数。这类问题包括算法的损失是最近对抗值的最小值,最近值的最大值,或最近值的线性组合。我们分析了这类问题在接受强盗反馈时的极大极小遗憾,证明了当使用最小或最大函数时,极大极小遗憾是$\tilde Ω(T^{2/3})$(所谓的硬在线学习问题),而当使用线性函数时,极大极小遗憾是$\tilde O(\sqrt{T})$(所谓的易学习问题).在此之前,唯一已知的可证明困难的在线学习问题是具有转换成本的多臂强盗问题。

英文摘要:

We study a new class of online learning problems where each of the online algorithm's actions is assigned an adversarial value, and the loss of the algorithm at each step is a known and deterministic function of the values assigned to its recent actions. This class includes problems where the algorithm's loss is the minimum over the recent adversarial values, the maximum over the recent values, or a linear combination of the recent values. We analyze the minimax regret of this class of problems when the algorithm receives bandit feedback, and prove that when the minimum or maximum functions are used, the minimax regret is $\tilde Ω(T^{2/3})$ (so called hard online learning problems), and when a linear function is used, the minimax regret is $\tilde O(\sqrt{T})$ (so called easy learning problems). Previously, the only online learning problem that was known to be provably hard was the multi-armed bandit with switching costs.

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。

↑