arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.14481cs.LGstat.ML
收藏

具有隐藏移动域的主动在线学习

Active Online Learning with Hidden Shifting Domains

Stanford University(斯坦福大学);University of Southern California(南加州大学);University of Arizona(亚利桑那大学)

Yining Chen, Haipeng Luo, Tengyu Ma, Chicheng Zhang

摘要:

在线机器学习系统需要适应领域的变化。同时,在每个时间步获取标签是昂贵的。我们提出了一个令人惊讶的简单的算法,自适应平衡其遗憾和标签查询的设置,其中数据流是从隐藏域的混合物。对于具有不经意对手的在线线性回归,我们提供了一个紧密的权衡,取决于隐藏域的持续时间和维度。我们的算法可以自适应地处理来自不同域的输入的交织跨度。我们还将我们的结果推广到非线性回归的假设类有界逃避维度和自适应对手。在人工数据集和真实数据集上的实验表明,该算法在相同的标记预算下,比均匀查询和贪婪查询具有更低的遗憾度。

英文摘要:

Online machine learning systems need to adapt to domain shifts. Meanwhile, acquiring label at every timestep is expensive. We propose a surprisingly simple algorithm that adaptively balances its regret and its number of label queries in settings where the data streams are from a mixture of hidden domains. For online linear regression with oblivious adversaries, we provide a tight tradeoff that depends on the durations and dimensionalities of the hidden domains. Our algorithm can adaptively deal with interleaving spans of inputs from different domains. We also generalize our results to non-linear regression for hypothesis classes with bounded eluder dimension and adaptive adversaries. Experiments on synthetic and realistic datasets demonstrate that our algorithm achieves lower regret than uniform queries and greedy queries with equal labeling budget.

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。

↑