arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.10327cs.LG
收藏

基于截断线性模型的无隐参数在线学习

Implicit Parameter-free Online Learning with Truncated Linear Models

Boston University(波士顿大学)

Keyi Chen, Ashok Cutkosky, Francesco Orabona

摘要:

无参数算法是不需要设置学习率的在线学习算法。他们实现了最佳的后悔相对于初始点和任何竞争对手之间的距离。然而,无参数算法不考虑损失的几何形状。最近,在随机优化文献中,有人提出使用截断线性下限,通过更紧密地建模损失来产生更好的性能。特别是,截断线性模型大大减少了过冲损失函数的最小值的问题。不幸的是,截断线性模型不能与无参数算法一起使用,因为更新的计算成本非常高。在本文中,我们提出了新的无参数算法,可以利用截断的线性模型,通过一个新的更新,有一个“隐式”的味道。基于一种新的分解的遗憾,新的更新是有效的,只需要一个梯度在每一步,永远不会超过截断模型的最小值,并保留了有利的参数自由属性。我们还进行了实证研究,证明我们的算法的实际效用。

英文摘要:

Parameter-free algorithms are online learning algorithms that do not require setting learning rates. They achieve optimal regret with respect to the distance between the initial point and any competitor. Yet, parameter-free algorithms do not take into account the geometry of the losses. Recently, in the stochastic optimization literature, it has been proposed to instead use truncated linear lower bounds, which produce better performance by more closely modeling the losses. In particular, truncated linear models greatly reduce the problem of overshooting the minimum of the loss function. Unfortunately, truncated linear models cannot be used with parameter-free algorithms because the updates become very expensive to compute. In this paper, we propose new parameter-free algorithms that can take advantage of truncated linear models through a new update that has an "implicit" flavor. Based on a novel decomposition of the regret, the new update is efficient, requires only one gradient at each step, never overshoots the minimum of the truncated model, and retains the favorable parameter-free properties. We also conduct an empirical study demonstrating the practical utility of our algorithms.

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。

↑