论文标题
隐藏的转移域的积极在线学习
Active Online Learning with Hidden Shifting Domains
论文作者
论文摘要
在线机器学习系统需要适应域移动。同时，在每个时间段上购买标签都是昂贵的。我们提出了一种令人惊讶的简单算法，该算法可以自适应地平衡其遗憾和标签查询的数量，以在数据流来自隐藏域的混合物中。对于在线线性回归和遗忘的对手，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。我们的算法可以适应地处理来自不同领域的输入的交织跨度。我们还将结果推广到具有有界的Eluder维度和适应性对手的假设类别的非线性回归。关于合成和现实数据集的实验表明，我们的算法比均匀标签预算的统一查询和贪婪的查询要低的遗憾。
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.
