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 2007.12160stat.MLcs.LG
收藏

数据流的在线鲁棒自适应学习

Online Robust and Adaptive Learning from Data Streams

The University of Tokyo(东京大学);TOYOTA MOTOR CORPORATION(丰田汽车公司);Kyushu Institute of Technology(九州工业大学)

Shintaro Fukushima, Atsushi Nitanda, Kenji Yamanishi

摘要:

在非平稳数据流的在线学习中,有必要鲁棒地学习离群值,并快速适应底层数据生成机制的变化。在本文中,我们提到的在线学习算法的鲁棒性和适应性,后者的前属性。在这两个属性之间有一个明显的权衡。这是一个基本的问题,量化和评估的权衡,因为它提供了重要的信息,数据生成机制。然而,没有以前的工作考虑了权衡定量。我们提出了一种新的算法称为随机逼近为基础的鲁棒性自适应算法(SRA)的权衡评估。SRA的核心思想是用有偏的随机逼近方案更新分布参数或充分统计量,同时丢弃随机更新值较大的数据点。我们解决了两个参数之间的关系:一个是随机逼近的步长,另一个是随机更新的范数的阈值参数。前者控制自适应性,后者控制鲁棒性。我们给出了一个理论分析的非渐近收敛的SRA存在离群值,这取决于步长和阈值参数。由于SRA是基于优化-最小化原理的,因此它是一种通用的算法,包括在线期望最大化算法和随机梯度下降算法。对合成数据集和真实数据集的实验表明,SRA优于以往的方法。

英文摘要:

In online learning from non-stationary data streams, it is necessary to learn robustly to outliers and to adapt quickly to changes in the underlying data generating mechanism. In this paper, we refer to the former attribute of online learning algorithms as robustness and to the latter as adaptivity. There is an obvious tradeoff between the two attributes. It is a fundamental issue to quantify and evaluate the tradeoff because it provides important information on the data generating mechanism. However, no previous work has considered the tradeoff quantitatively. We propose a novel algorithm called the stochastic approximation-based robustness-adaptivity algorithm (SRA) to evaluate the tradeoff. The key idea of SRA is to update parameters of distribution or sufficient statistics with the biased stochastic approximation scheme, while dropping data points with large values of the stochastic update. We address the relation between the two parameters: one is the step size of the stochastic approximation, and the other is the threshold parameter of the norm of the stochastic update. The former controls the adaptivity and the latter does the robustness. We give a theoretical analysis for the non-asymptotic convergence of SRA in the presence of outliers, which depends on both the step size and threshold parameter. Because SRA is formulated on the majorization-minimization principle, it is a general algorithm that includes many algorithms, such as the online EM algorithm and stochastic gradient descent. Empirical experiments for both synthetic and real datasets demonstrated that SRA was superior to previous methods.

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。

↑