# Fast and Flexible Temporal Point Processes with Triangular Maps

arXiv: https://arxiv.org/abs/2006.12631 · HTML: https://mlsanity.com/paper/2006.12631/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2020.

## Built on by (most cited first, 30 of 30)

- [Neural Temporal Point Processes: A Review](https://mlsanity.com/paper/2104.03528/) (2021)
- [ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling](https://mlsanity.com/paper/2402.10635/) (2024)
- [Exploring Generative Neural Temporal Point Process](https://mlsanity.com/paper/2208.01874/) (2022)
- [Add and Thin: Diffusion for Temporal Point Processes](https://mlsanity.com/paper/2311.01139/) (2023)
- [On the Predictive Accuracy of Neural Temporal Point Process Models for Continuous-time Event Data](https://mlsanity.com/paper/2306.17066/) (2023)
- [Unlocking Point Processes through Point Set Diffusion](https://mlsanity.com/paper/2410.22493/) (2024)
- [Poisson Variational Autoencoder](https://mlsanity.com/paper/2405.14473/) (2024)
- [Deep Continuous-Time State-Space Models for Marked Event Sequences](https://mlsanity.com/paper/2412.19634/) (2024)
- [An Empirical Study: Extensive Deep Temporal Point Process](https://mlsanity.com/paper/2110.09823/) (2021)
- [Interacting Diffusion Processes for Event Sequence Forecasting](https://mlsanity.com/paper/2310.17800/) (2023)
- [Integration-free Training for Spatio-temporal Multimodal Covariate Deep Kernel Point Processes](https://mlsanity.com/paper/2310.05485/) (2023)
- [EventFlow: Forecasting Temporal Point Processes with Flow Matching](https://mlsanity.com/paper/2410.07430/) (2024)
- [Edit-Based Flow Matching for Temporal Point Processes](https://mlsanity.com/paper/2510.06050/) (2025)
- [Non-Autoregressive Diffusion-based Temporal Point Processes for Continuous-Time Long-Term Event Prediction](https://mlsanity.com/paper/2311.01033/) (2023)
- [FaDIn: Fast Discretized Inference for Hawkes Processes with General Parametric Kernels](https://mlsanity.com/paper/2210.04635/) (2022)
- [A Differentiable Point Process with Its Application to Spiking Neural Networks](https://mlsanity.com/paper/2106.00901/) (2021)
- [Modelling Direct Messaging Networks with Multiple Recipients for Cyber Deception](https://mlsanity.com/paper/2111.11932/) (2021)
- [Nonlinear Hawkes Processes in Time-Varying System](https://mlsanity.com/paper/2106.04844/) (2021)
- [Advances in Temporal Point Processes: Bayesian, Neural, and LLM Approaches](https://mlsanity.com/paper/2501.14291/) (2025)
- [TPP-SD: Accelerating Transformer Point Process Sampling with Speculative Decoding](https://mlsanity.com/paper/2507.09252/) (2025)
- [DriPP: Driven Point Processes to Model Stimuli Induced Patterns in M/EEG Signals](https://mlsanity.com/paper/2112.06652/) (2021)
- [Generative Unordered Flow for Set-Structured Data Generation](https://mlsanity.com/paper/2501.17770/) (2025)
- [Latent Discretization for Continuous-time Sequence Compression](https://mlsanity.com/paper/2212.13659/) (2022)
- [Unmixing Noise from Hawkes Process to Model Learned Physiological Events](https://mlsanity.com/paper/2406.16938/) (2024)
- [Neural Diffusion Intensity Models for Point Process Data](https://mlsanity.com/paper/2602.24083/) (2026)
- [Efficient Temporal Point Processes via Monotone Alternating Splines](https://mlsanity.com/paper/2607.01752/) (2026)
- [From Jumps to Signatures: a Generative Method for Temporal Point Processes](https://mlsanity.com/paper/2607.06652/) (2026)
- [Model-Based Reinforcement Learning for Heterogeneous Multi-Robot Task Assignment Under Distribution Shifts](https://mlsanity.com/paper/2608.21554/) (2026)
- [Scan-Parallel Variational Inference for event-driven Latent Jump Models](https://mlsanity.com/paper/2610.12986/) (2026)
- [Modeling the Arrival Time of Information-Bearing Events in Natural Language](https://mlsanity.com/paper/2610.14212/) (2026)

## Abstract (arXiv)

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.