针对准周期时间序列，提出一种渐进训练的递归生成模型，提升长期建模稳定性。
Approximately Equivariant Recurrent Generative Models for Quasi-Periodic Time Series with a Progressive Training Scheme
- 采用递归变分自编码器，设计近似时移等变结构以匹配准周期数据特征
- 通过逐步增加序列长度的训练策略，实现长时序稳定收敛，性能超越多个基准模型
- 适合处理准周期或近平稳时间序列，尤其在复杂周期信号生成中表现突出
我们提出一种基于递归变分自编码器的生成模型——AEQ-RVAE-ST，用于时间序列建模。递归层在处理长序列时常面临优化不稳定与收敛困难问题。为此，我们引入一种渐进式训练方案，逐步增加序列长度，从而稳定优化过程并实现对长时序的一致学习。通过将已有组件组合为具有近似时移等变性的递归结构，模型引入了符合准周期及近平稳时间序列结构的归纳偏置。在多个基准数据集上，AEQ-RVAE-ST在准周期数据上达到或超过现有先进生成模型的表现，同时在更不规则信号上也保持竞争力。评估指标包括ELBO、Fréchet距离、判别性指标以及潜在空间嵌入的可视化结果。
原文摘要 · Abstract (English)
We present a simple yet effective generative model for time series, based on a Recurrent Variational Autoencoder that we refer to as AEQ-RVAE-ST. Recurrent layers often struggle with unstable optimization and poor convergence when modeling long sequences. To address these limitations, we introduce a training scheme that subsequently increases the sequence length, stabilizing optimization and enabling consistent learning over extended horizons. By composing known components into a recurrent, approximately time-shift-equivariant topology, our model introduces an inductive bias that aligns with the structure of quasi-periodic and nearly stationary time series. Across several benchmark datasets, AEQ-RVAE-ST matches or surpasses state-of-the-art generative models, particularly on quasi-periodic data, while remaining competitive on more irregular signals. Performance is evaluated through ELBO, Fréchet Distance, discriminative metrics, and visualizations of the learned latent embeddings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。