Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement
扩散、去噪和解纠缠的生成时间序列预测
Time series forecasting has been a widely explored task that is of great importance in many applications.
时间序列预测是一个广泛研究的课题，在许多应用中具有重要意义。
一个广泛研究的课题：a widely explored task
具有重要意义：is of great importance
that is of great importance in many applications
However, it is common that real-world time series data are recorded in a short time period, which results in a big gap between the deep model and the limited and noisy time series.
然而，现实世界中的时间序列数据通常是在较短的时间段内记录的，这导致了深度模型与有限的、有噪声的时间序列之间存在很大的差距。
in a short time period
短时间内
In this work, we propose to address the time series forecasting problem with generative modeling and propose a bidirectional variational auto-encoder equipped with diffusion, denoise and disentanglement namely D3VAE.
Specifically, a coupled diffusion probabilistic model is proposed to augment the time series data without increasing the aleatoric uncertainty and implement a more tractable inference process with BVAE.
具体而言，提出了一种耦合扩散概率模型，在不增加随机不确定性的前提下对时间序列数据进行扩充，并利用BVAE实现了更易处理的推理过程.
the aleatoric uncertainty
随即不确定性
/æliˈeɪtəri/
adj.任意的；偶然的
To ensure the generated series move toward the true target, we further propose to adapt and integrate the multiscale denoising score matching into the diffusion process for time series forecasting.
为了保证生成的序列更接近真实目标，我们进一步提出了将多尺度去噪得分匹配融入到扩散过程中进行时间序列预测.
move toward the true target：接近真实目标
adapt and integrate the multiscale denoising score matching
提出了将多尺度去噪得分匹配融入
In addition, to enhance the interpretability and stability of the prediction, we treat the latent variable in a multivariate manner and disentangle them on top of minimizing total correlation.
此外，为了提高预测的可解释性和稳定性，我们以多元方式处理潜在变量，并在最小化总相关性的基础上将它们分开。
to enhance the interpretability and stability of the prediction
为了提高预测的可解释性和稳定性
on top of minimizing total correlation
在最小化总相关性的基础上
a more tractable inference process
更 易处理的推理过程
Original: https://blog.csdn.net/weixin_45193103/article/details/128355836
Author: anzrs
Title: 论文里的好句子（5）
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/724174/
转载文章受原作者版权保护。转载请注明原作者出处！