EventFlow: Forecasting Temporal Point Processes with Flow Matching

ArXi:2410.07430v3 Announce Type: replace 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.