用新采样器让时间序列生成快30倍且更清晰
Sawtooth Sampling for Time Series Denoising Diffusion Implicit Models
- 设计锯齿形采样器加速扩散模型逆过程
- 相比标准方法速度提升30倍，生成质量更好
- 可通用适配任意预训练扩散模型
去噪扩散概率模型（DDPM）能生成合成时间序列数据以提升分类器性能，但其采样过程计算成本高。本文结合隐式扩散模型与一种新型锯齿形采样器，加速反向生成过程，并可应用于任何预训练的扩散模型。实验表明，该方法在保持生成质量的前提下，相较标准基线实现30倍的速度提升，显著改善了分类任务中生成序列的质量。
原文摘要 · Abstract (English)
Denoising Diffusion Probabilistic Models (DDPMs) can generate synthetic timeseries data to help improve the performance of a classifier, but their sampling process is computationally expensive. We address this by combining implicit diffusion models with a novel Sawtooth Sampler that accelerates the reverse process and can be applied to any pretrained diffusion model. Our approach achieves a 30 times speed-up over the standard baseline while also enhancing the quality of the generated sequences for classification tasks.
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。