When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting
When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting
复制标题
当刚性受到损害时：概率分层时间序列预测的软一致性正则化
DOI：
10.1145/3580305.3599547
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Prakash, B. Aditya
中科院分区：
文献类型：
--
作者：
Kamarthi, Harshavardhan;Kong, Lingkai;Rodriguez, Alexander;Zhang, Chao;Prakash, B. Aditya
概率分层时间序列预测是时间序列预测的一个重要变种，其目标是对具有分层关系的多变量时间序列进行建模和预测。以前的工作假设给定层次结构上的严格一致性，并且不能很好地适应显示偏离这一假设的真实世界数据。此外，最近最新的神经概率方法也对点预测和预测分布的样本施加层次关系。这不能说明完整的预测分布与层次结构一致，并导致预测校准不佳。我们缩小了这两个差距，并提出了PROFHiT，这是一个概率层次预测模型，联合建模整个层次结构上的预测分布。PROFHiT(1)使用灵活的概率贝叶斯方法，(2)引入软分布一致性正则化，利用底层层次结构的信息实现整个预测分布的端到端学习。这使得校准的预测以及适应现实生活中的数据具有不同的等级一致性。PROFHiT在广泛的数据集一致性上提供了41-88%的准确度和显著更好的校准性能。此外，PROFHiT能够适应缺失数据，即使高达10%的输入时间序列数据缺失，PROFHiT也能提供可靠的预测，而其他方法的性能严重下降70%以上
Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting, where the goal is to model and forecast multivariate time-series that have hierarchical relations. Previous works assume rigid consistency over the given hierarchies and do not adapt well to real-world data that show deviation from this assumption. Moreover, recent state-of-art neural probabilistic methods also impose hierarchical relations on point predictions and samples of the predictive distribution. This does not account for full forecast distributions being consistent with the hierarchy and leading to poorly calibrated forecasts. We close both these gaps and propose PROFHiT, a probabilistic hierarchical forecasting model that jointly models forecast distributions over the entire hierarchy. PROFHiT (1) uses a flexible probabilistic Bayesian approach and (2) introduces soft distributional consistency regularization that enables end-to-end learning of the entire forecast distribution leveraging information from the underlying hierarchy. This enables calibrated forecasts as well as adaptation to real-life data with varied hierarchical consistency. PROFHiT provides 41-88% better performance in accuracy and significantly better calibration over a wide range of dataset consistency. Furthermore, PROFHiT adapts to missing data and can provide reliable forecasts even if up to 10% of input time-series data is missing, whereas other methods' performance severely degrades by over 70%
登录
查看更多内容
同时期分层时间序列预测的博弈论最优协调
DOI：
--
发表时间：
2015
期刊：
影响因子：
--
作者：
T. Erven;Jairo Cugliari
通讯作者：
Jairo Cugliari
使用 Auto ML 提高黑色素瘤诊断系统的性能
DOI：
--
发表时间：
2023
期刊：
影响因子：
--
作者：
Inoue Manabu;Yoshimoto Takeshi;Tanaka Kanta;Koge Junpei;Shiozawa Masayuki;Nishii Tatsuya;Ohta Yasutoshi;Fukuda Tetsuya;Satow Tetsu;Kataoka Hiroharu;Yamagami Hiroshi;Ihara Masafumi;Koga Masatoshi;Mlynash Michael;Albers Gregory W.;Toyoda Kazunori;正木達也・北畠直人・飛塚丈輝・花崎和寿・張 維倫・永岡 隆
通讯作者：
正木達也・北畠直人・飛塚丈輝・花崎和寿・張 維倫・永岡 隆
DOI：
--
发表时间：
2017
期刊：
影响因子：
--
作者：
Julie Novak;S. Mcgarvie;B. Garcia
通讯作者：
B. Garcia
DOI：
--
发表时间：
2021
期刊：
Journal of Business & Economic Statistics
影响因子：
--
作者：
Shanika L. Wickramasuriya
通讯作者：
Shanika L. Wickramasuriya