用推测解码加速时间点过程采样，速度提升2-6倍。
TPP-SD: Accelerating Transformer Point Process Sampling with Speculative Decoding
- 用小模型预生成候选事件，大模型并行验证。
- 采样速度提升2-6倍，分布与传统方法一致。
- 适合需要快速生成时间序列的场景。
我们提出TPP-SD，一种通过借鉴语言模型中的推测解码（SD）技术来加速Transformer时间点过程（TPP）采样的新方法。基于TPP的剔除算法与语言模型推测解码的结构相似性，我们构建了一个高效采样框架：利用小型草稿模型生成多个候选事件，并由大型目标模型并行验证。TPP-SD在保持与自回归采样相同输出分布的同时，显著提升效率。在合成与真实数据集上的实验表明，该方法生成的样本分布与标准方法完全一致，但速度提升2-6倍。消融实验分析了草稿长度和草稿模型规模等超参数对采样效率的影响。TPP-SD弥合了强大Transformer TPP模型与快速序列采样实际需求之间的差距。
原文摘要 · Abstract (English)
We propose TPP-SD, a novel approach that accelerates Transformer temporal point process (TPP) sampling by adapting speculative decoding (SD) techniques from language models. By identifying the structural similarities between thinning algorithms for TPPs and speculative decoding for language models, we develop an efficient sampling framework that leverages a smaller draft model to generate multiple candidate events, which are then verified by the larger target model in parallel. TPP-SD maintains the same output distribution as autoregressive sampling while achieving significant acceleration. Experiments on both synthetic and real datasets demonstrate that our approach produces samples from identical distributions as standard methods, but with 2-6$\times$ speedup. Our ablation studies analyze the impact of hyperparameters such as draft length and draft model size on sampling efficiency. TPP-SD bridges the gap between powerful Transformer TPP models and the practical need for rapid sequence sampling.
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。