Speculative Sampling for Parametric Temporal Point Processes
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918166797484032 |
|---|---|
| author | Biloš, Marin Schneider, Anderson Nevmyvaka, Yuriy |
| author_facet | Biloš, Marin Schneider, Anderson Nevmyvaka, Yuriy |
| contents | Temporal point processes are powerful generative models for event sequences that capture complex dependencies in time-series data. They are commonly specified using autoregressive models that learn the distribution of the next event from the previous events. This makes sampling inherently sequential, limiting efficiency. In this paper, we propose a novel algorithm based on rejection sampling that enables exact sampling of multiple future values from existing TPP models, in parallel, and without requiring any architectural changes or retraining. Besides theoretical guarantees, our method demonstrates empirical speedups on real-world datasets, bridging the gap between expressive modeling and efficient parallel generation for large-scale TPP applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20031 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Speculative Sampling for Parametric Temporal Point Processes Biloš, Marin Schneider, Anderson Nevmyvaka, Yuriy Machine Learning Temporal point processes are powerful generative models for event sequences that capture complex dependencies in time-series data. They are commonly specified using autoregressive models that learn the distribution of the next event from the previous events. This makes sampling inherently sequential, limiting efficiency. In this paper, we propose a novel algorithm based on rejection sampling that enables exact sampling of multiple future values from existing TPP models, in parallel, and without requiring any architectural changes or retraining. Besides theoretical guarantees, our method demonstrates empirical speedups on real-world datasets, bridging the gap between expressive modeling and efficient parallel generation for large-scale TPP applications. |
| title | Speculative Sampling for Parametric Temporal Point Processes |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.20031 |