arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.00636cs.LGphysics.ao-phstat.ML
收藏

反向预测:利用时间不对称性在时间序列预测中的证明概念

Retrodictive Forecasting: A Proof-of-Concept for Exploiting Temporal Asymmetry in Time Series Prediction

ENERGY-Lab, Université de La Réunion(能源实验室,拉雷翁大学)

Cedric Damour

AI总结:

本文提出反向预测方法,利用时间不对称性在时间序列预测中实现更优的预测效果,通过逆向CVAE和归一化流先验,验证了反向预测在不可逆动态中的有效性。

摘要:

我们提出了一种时间序列的反向预测范式:即不是从过去预测未来,而是通过在条件变分自编码器(CVAE)上进行逆向最大似然估计,确定最能解释观测到的现在的情况。这种条件设置是贝叶斯反演的统计建模选择;它并不断言未来事件导致过去的观测。该方法在信息论的时间箭头度量上具有理论基础:正向和时间反转轨迹集合之间的对称化Kullback-Leibler散度提供了概念上的依据和适用性的操作性GO/NO-GO诊断。我们将该范式实现为逆向CVAE上的最大似然估计,使用学习到的RealNVP归一化流先验,并在六个时间序列案例上进行评估:四个具有可控时间不对称性的合成过程和两个ERA5再分析数据集(风速和太阳能辐照度)。这项工作有四个贡献:(i)正式的反向推断公式;(ii)逆向CVAE架构;(iii)无模型的不可逆性诊断;(iv)可验证的验证协议,包含四个预设的预测。所有预设的预测都得到了实证支持:诊断正确分类了所有六个案例;学习到的流先验在GO案例上优于各向同性高斯基线;逆向最大似然估计在时间可逆动态上没有虚假优势;在不可逆GO案例中,其RMSE相对于正向基线具有竞争性或优越性,与正向MLP相比,在ERA5太阳能辐照度上统计显著减少了17.7%。这些结果提供了一个结构化的证明概念,表明在统计时间不可逆性存在且可利用时,反向预测可以成为传统正向预测的可行替代方案。

英文摘要:

We propose a retrodictive forecasting paradigm for time series: instead of predicting the future from the past, we identify the future that best explains the observed present via inverse MAP optimization over a Conditional Variational Autoencoder (CVAE). This conditioning is a statistical modeling choice for Bayesian inversion; it does not assert that future events cause past observations. The approach is theoretically grounded in an information-theoretic arrow-of-time measure: the symmetrized Kullback-Leibler divergence between forward and time-reversed trajectory ensembles provides both the conceptual rationale and an operational GO/NO-GO diagnostic for applicability. We implement the paradigm as MAP inference over an inverse CVAE with a learned RealNVP normalizing-flow prior and evaluate it on six time series cases: four synthetic processes with controlled temporal asymmetry and two ERA5 reanalysis datasets (wind speed and solar irradiance). The work makes four contributions: (i) a formal retrodictive inference formulation; (ii) an inverse CVAE architecture; (iii) a model-free irreversibility diagnostic; and (iv) a falsifiable validation protocol with four pre-specified predictions. All pre-specified predictions are empirically supported: the diagnostic correctly classifies all six cases; the learned flow prior improves over an isotropic Gaussian baseline on GO cases; the inverse MAP yields no spurious advantage on time-reversible dynamics; and on irreversible GO cases, it achieves competitive or superior RMSE relative to forward baselines, with a statistically significant 17.7% reduction over a forward MLP on ERA5 solar irradiance. These results provide a structured proof-of-concept that retrodictive forecasting can constitute a viable alternative to conventional forward prediction when statistical time-irreversibility is present and exploitable.

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。

↑