arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.01577cs.LGmath.OCstat.ML
收藏

静态与动态遗憾最小化之间的等价性

An Equivalence Between Static and Dynamic Regret Minimization

Università degli Studi di Milano(米兰大学);Politecnico di Milano(米兰理工大学);KAUST(阿卜杜拉国王科技大学)

Andrew Jacobsen, Francesco Orabona

AI总结:

该研究证明在线凸优化线性损失下动态与静态遗憾最小化等价,揭示损失方差与比较器可变性的下界权衡,首次证伪平方路径长度自适应的遗憾界,提出局部平滑可变性概念与对应动态遗憾保证算法。

摘要:

我们研究在线凸优化中的动态遗憾最小化问题,其目标是最小化算法的累积损失与任意比较器序列的累积损失之间的差值。尽管该主题的研究文献十分丰富,但目前仍缺乏用于分析和设计这些算法的统一框架。本文证明,对于线性损失,动态遗憾最小化等价于扩展决策空间中的静态遗憾最小化。基于这一简单结论,我们揭示了一条下界前沿,该前沿在损失方差带来的惩罚与比较器序列可变性带来的惩罚之间存在权衡关系,并提供了一个可实现该前沿上任意保证的框架。据此,我们还首次证明,通过自适应匹配任意比较器序列的平方路径长度以实现遗憾$R_{T}(u_{1},\dots,u_{T})\le O(\sqrt{T\sum_{t} \\|u_{t}-u_{t+1}\\|^{2}})$是不可能的。不过,利用我们的框架,我们提出了一种基于局部平滑比较器序列$\bar u_{1}, \dots, \bar u_{T}$的可变性替代概念,并给出了一种算法,其动态遗憾保证为$R_{T}(u_{1},\dots,u_{T})\le \tilde O(\sqrt{T\sum_{i}\\|\bar u_{i}-\bar u_{i+1}\\|^{2}})$,同时在最坏情况下仍能匹配通常的路径长度依赖关系,仅相差多重对数项。

英文摘要:

We study the problem of dynamic regret minimization in online convex optimization, in which the objective is to minimize the difference between the cumulative loss of an algorithm and that of an arbitrary sequence of comparators. While the literature on this topic is very rich, a unifying framework for the analysis and design of these algorithms is still missing. In this paper we show that for linear losses, dynamic regret minimization is equivalent to static regret minimization in an extended decision space. Using this simple observation, we show that there is a frontier of lower bounds trading off penalties due to the variance of the losses and penalties due to variability of the comparator sequence, and provide a framework for achieving any of the guarantees along this frontier. As a result, we also prove for the first time that adapting to the squared path-length of an arbitrary sequence of comparators to achieve regret $R_{T}(u_{1},\dots,u_{T})\le O(\sqrt{T\sum_{t} \|u_{t}-u_{t+1}\|^{2}})$ is impossible. However, using our framework we introduce an alternative notion of variability based on a locally-smoothed comparator sequence $\bar u_{1}, \dots, \bar u_{T}$, and provide an algorithm guaranteeing dynamic regret of the form $R_{T}(u_{1},\dots,u_{T})\le \tilde O(\sqrt{T\sum_{i}\|\bar u_{i}-\bar u_{i+1}\|^{2}})$, while still matching in the worst case the usual path-length dependencies up to polylogarithmic terms.

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。

↑