论文标题
预测时间序列的双重修复生成模型
Dual reparametrized Variational Generative Model for Time-Series Forecasting
论文作者
论文摘要
本文提出了DualVDT，这是一个预测时间序列的生成模型。引入了在变化自动编码器（VAE）上引入双重修复的变异机制，以更严格模型的下限（ELBO），从而在分析上证明了进步性能。该机制利用了基于潜在评分的生成模型（SGM），通过反向时间随机微分方程和变异祖先采样明确地剥夺了潜在载体在潜在载体上积累的扰动。 DeNo的潜在分布的后部与双重修复的变分密度融合在一起。 ELBO中的KL差异将减少以达到模型的更好结果。本文还提出了一种潜在的注意机制，以明确提取多元依赖性。通过通过构造的局部拓扑和暂时的智慧来同时建立本地时间依赖性。多个数据集上的经过验证的实验说明了DualVDT，具有新型的双重重新培训结构，该结构通过结合局部 - 周期性推断的反向动力学来证明潜在的扰动，并在分析和实验上具有先进的性能。
This paper propose DualVDT, a generative model for Time-series forecasting. Introduced dual reparametrized variational mechanisms on variational autoencoder (VAE) to tighter the evidence lower bound (ELBO) of the model, prove the advance performance analytically. This mechanism leverage the latent score based generative model (SGM), explicitly denoising the perturbation accumulated on latent vector through reverse time stochastic differential equation and variational ancestral sampling. The posterior of denoised latent distribution fused with dual reparametrized variational density. The KL divergence in ELBO will reduce to reach the better results of the model. This paper also proposed a latent attention mechanisms to extract multivariate dependency explicitly. Build the local temporal dependency simultaneously in factor wised through constructed local topology and temporal wised. The proven and experiment on multiple datasets illustrate, DualVDT, with a novel dual reparametrized structure, which denoise the latent perturbation through the reverse dynamics combining local-temporal inference, has the advanced performance both analytically and experimentally.
