To provide rigorous uncertainty quantification for online learning models, we develop a framework for constructing uncertainty sets that provably control risk -- such as coverage of confidence intervals, false negative rate, or F1 score -- in the online setting. This extends conformal prediction to apply to a larger class of online learning problems. Our method guarantees risk control at any user-specified level even when the underlying data distribution shifts drastically, even adversarially, over time in an unknown fashion. The technique we propose is highly flexible as it can be applied with any base online learning algorithm (e.g., a deep neural network trained online), requiring minimal implementation effort and essentially zero additional computational cost. We further extend our approach to control multiple risks simultaneously, so the prediction sets we generate are valid for all given risks. To demonstrate the utility of our method, we conduct experiments on real-world tabular time-series data sets showing that the proposed method rigorously controls various natural risks. Furthermore, we show how to construct valid intervals for an online image-depth estimation problem that previous sequential calibration schemes cannot handle.
翻译:为了为在线学习模式提供严格的不确定性量化,我们制定了一个框架,用于构建不确定性框架,以在网上设置中控制风险 -- -- 例如信任间隔、虚假负率或F1分的覆盖面,从而将符合的预测扩展至适用于更大类别的在线学习问题。我们的方法保证在任何用户指定水平上进行风险控制,即使基础数据分布随着时间的推移发生急剧变化,甚至是对抗性变化,也不为人所知。我们提出的技术非常灵活,因为它可以适用于任何基础在线学习算法(例如,在网上培训的深神经网络),需要最低限度的执行努力和基本上零额外计算成本。我们进一步扩展了同时控制多重风险的方法,因此我们产生的预测组对所有风险都是有效的。为了展示我们的方法的效用,我们在现实世界的表格时间序列数据集上进行实验,表明拟议的方法严格控制各种自然风险。此外,我们展示了如何为以往的顺序校准计划无法处理的在线图像深度估算问题构建有效间隔期。