Fast and Flexible Temporal Point Processes with Triangular Maps
This work addresses the computational bottleneck in modeling continuous-time event data for applications like event prediction, offering significant speed improvements for researchers and practitioners in fields such as healthcare or finance.
The authors tackled the inefficiency of sequential recurrent neural networks in temporal point processes by introducing TriTPP, a non-recurrent model using normalizing flows that enables parallel sampling and likelihood computation, achieving orders of magnitude faster sampling while matching the flexibility of existing methods.
Temporal point process (TPP) models combined with recurrent neural networks provide a powerful framework for modeling continuous-time event data. While such models are flexible, they are inherently sequential and therefore cannot benefit from the parallelism of modern hardware. By exploiting the recent developments in the field of normalizing flows, we design TriTPP -- a new class of non-recurrent TPP models, where both sampling and likelihood computation can be done in parallel. TriTPP matches the flexibility of RNN-based methods but permits orders of magnitude faster sampling. This enables us to use the new model for variational inference in continuous-time discrete-state systems. We demonstrate the advantages of the proposed framework on synthetic and real-world datasets.