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 2409.18267cs.LGstat.ML
收藏

使用动态损失加权提升预测稳定性的改进效果

Using dynamic loss weighting to boost improvements in forecast stability

KU Leuven(鲁汶大学)

Daan Caljon, Jeff Vercauteren, Simon De Vos, Wouter Verbeke, Jente Van Belle

AI总结:

针对滚动原点预测不稳定性问题,本文研究动态损失加权算法,在不牺牲准确率的前提下进一步提升预测稳定性,还提出了任务感知随机加权的扩展方法。

摘要:

滚动原点预测不稳定性指的是当新数据点可用时更新预测,导致特定时期的预测结果存在变异性。近期,针对单变量时间序列点预测的N-BEATS模型被提出扩展版本,将预测稳定性作为除准确率之外的额外优化目标。研究表明,通过最小化同时包含预测误差和预测不稳定性分量的复合损失函数,并使用静态超参数控制稳定性的影响,可以在不损害准确率的前提下获得更稳定的预测结果。本文通过实证研究,探究在训练过程中调整损失权重的动态损失加权算法,能否在不牺牲准确率的前提下进一步提升稳定性。我们证明现有动态损失加权方法可以实现这一目标,并分析了其背后的潜在原因。此外,我们提出了随机加权(Random Weighting)方法的扩展版本——任务感知随机加权(Task-Aware Random Weighting),该方法同样能够实现上述目标。

英文摘要:

Rolling origin forecast instability refers to variability in forecasts for a specific period induced by updating the forecast when new data points become available. Recently, an extension to the N-BEATS model for univariate time series point forecasting was proposed to include forecast stability as an additional optimization objective, next to accuracy. It was shown that more stable forecasts can be obtained without harming accuracy by minimizing a composite loss function that contains both a forecast error and a forecast instability component, with a static hyperparameter to control the impact of stability. In this paper, we empirically investigate whether further improvements in stability can be obtained without compromising accuracy by applying dynamic loss weighting algorithms, which change the loss weights during training. We show that existing dynamic loss weighting methods can achieve this objective and provide insights into why this might be the case. Additionally, we propose an extension to the Random Weighting approach -- Task-Aware Random Weighting -- which also achieves this objective.

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。

↑