arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1303.3754cs.LG
收藏

非平稳在线学习的最后一步回归算法

A Last-Step Regression Algorithm for Non-Stationary Online Learning

The Technion(以色列理工学院)

Edward Moroshko, Koby Crammer

摘要:

学习者在标准在线学习中的目标是保持平均损失接近某类中表现最好的单个功能的损失。在许多现实世界的问题中,例如对项目进行评级或排名,在算法的运行时间期间不存在单个最佳目标函数,而是最佳(局部)目标函数随时间漂移。我们开发了一种新的最后一步极小极大优化算法的上下文中的漂移。我们分析了算法在最坏情况下的遗憾框架,并表明,它保持了平均损失接近的最佳缓慢变化的线性函数序列,只要漂移的总是次线性的。在某些情况下,我们的界限改善现有的界限,此外,该算法遭受对数遗憾时,没有漂移。我们还建立在H_infinity滤波器和它的界限,并开发和分析第二个算法的漂移设置。合成模拟证明了我们的算法在最坏情况下的恒定漂移设置的优势。

英文摘要:

The goal of a learner in standard online learning is to maintain an average loss close to the loss of the best-performing single function in some class. In many real-world problems, such as rating or ranking items, there is no single best target function during the runtime of the algorithm, instead the best (local) target function is drifting over time. We develop a novel last-step minmax optimal algorithm in context of a drift. We analyze the algorithm in the worst-case regret framework and show that it maintains an average loss close to that of the best slowly changing sequence of linear functions, as long as the total of drift is sublinear. In some situations, our bound improves over existing bounds, and additionally the algorithm suffers logarithmic regret when there is no drift. We also build on the H_infinity filter and its bound, and develop and analyze a second algorithm for drifting setting. Synthetic simulations demonstrate the advantages of our algorithms in a worst-case constant drift setting.

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。

↑