Halo：通过异方差估计提升预测精度
原标题：Halo: Improving forecast accuracy through heteroscedastic estimation
AI 摘要
论文提出 Halo 方法，在现有深度时间序列预测模型上增加一个估计分布尺度参数的输出，并用匹配的负对数似然训练。作者在 transformer、图网络+VAE、单层卷积网络三种 SOTA 模型上，用高斯和拉普拉斯损失在五个电力价格市场基准测试，30 组模型-市场-指标对比中有 28 组改善 MSE 和 MAE，平均 MSE 降低 2.6% 至 16.5%，平均 MAE 降低 1.7% 至 11.0%。研究发现尺度估计来自第二个投影头还是完整并行网络影响不大，且无需重新调参即可在已调优的点估计基线上获得提升。
正文节选
Halo: Improving forecast accuracy through heteroscedastic estimation Abstract Heteroscedastic forecasting, where a network estimates a scale parameter alongside a location parameter, is normally motivated by uncertainty quantification. This paper shows it also improves the point estimate, in contrast to reported negative results for heteroscedastic estimation outside time series. Halo is a modification that reuses an existing deep forecaster’s architecture, giving it a second output for the scal