Temporal point processes (TPPs) are a fundamental tool for modeling event sequences in continuous time, but most existing approaches rely on autoregressive parameterizations that are limited by their sequential sampling. Recent non-autoregressive, diffusion-style models mitigate these issues by jointly interpolating between noise and data through event insertions and deletions in a discrete Markov chain. In this work, we generalize this perspective and introduce an Edit Flow process for TPPs that transports noise to data via insert, delete, and substitute edit operations. By learning the instantaneous edit rates within a continuous-time Markov chain framework, we attain a flexible and efficient model that effectively reduces the total number of necessary edit operations during generation. Empirical results demonstrate the generative flexibility of our unconditionally trained model in a wide range of unconditional and conditional generation tasks on benchmark TPPs.

翻译：时序点过程（TPPs）是连续时间中建模事件序列的基本工具，但现有方法大多依赖于自回归参数化，其受限于顺序采样。近期非自回归的扩散式模型通过在离散马尔可夫链中通过事件插入和删除在噪声与数据间进行联合插值，缓解了这些问题。本文中，我们推广了这一视角，为TPPs引入了一种编辑流过程，该过程通过插入、删除和替换编辑操作将噪声传输至数据。通过在连续时间马尔可夫链框架内学习瞬时编辑率，我们获得了一个灵活高效的模型，该模型在生成过程中有效减少了所需编辑操作的总数。实证结果表明，我们无条件训练的模型在基准TPPs上的广泛无条件与条件生成任务中展现出卓越的生成灵活性。