Continuous-time event sequences, in which events occur at irregular intervals, are ubiquitous across a wide range of industrial and scientific domains. The contemporary modeling paradigm is to treat such data as realizations of a temporal point process, and in machine learning it is common to model temporal point processes in an autoregressive fashion using a neural network. While autoregressive models are successful in predicting the time of a single subsequent event, their performance can degrade when forecasting longer horizons due to cascading errors and myopic predictions. We propose EventFlow, a non-autoregressive generative model for temporal point processes. The model builds on the flow matching framework in order to directly learn joint distributions over event times, side-stepping the autoregressive process. EventFlow is simple to implement and achieves a 20%-53% lower forecast error than the nearest baseline on standard TPP benchmarks while simultaneously using fewer model calls at sampling time.

翻译：连续时间事件序列（事件以不规则间隔发生）广泛存在于工业和科学领域。当前的建模范式是将此类数据视为时间点过程的实现，在机器学习中，通常使用神经网络以自回归方式对时间点过程建模。尽管自回归模型在预测单个后续事件发生时间方面表现良好，但由于级联误差和短视预测，其在更长预测周期内的性能会下降。我们提出EventFlow，一种用于时间点过程的非自回归生成模型。该模型基于流匹配框架，直接学习事件时间上的联合分布，从而绕开自回归过程。EventFlow实现简单，在标准时间点过程基准测试中，其预测误差比最接近的基线方法低20%-53%，同时在采样时使用的模型调用次数更少。