# TPP-SD: Accelerating Transformer Point Process Sampling with Speculative Decoding

arXiv: https://arxiv.org/abs/2507.09252 · HTML: https://mlsanity.com/paper/2507.09252/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Speculative decoding, one of 12 directions in Efficient LLM inference and serving.
- Builds on 15 of its 40 references that are in the map.
- First posted on arXiv 12 Jul 2025.

## Placed in

- Efficient LLM inference and serving / [Speculative decoding](https://mlsanity.com/inference/speculative-decoding/)

## Builds on (most cited first, 15 of 15)

- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [Transformer Hawkes Process](https://mlsanity.com/paper/2002.09291/) (2020)
- [Intensity-Free Learning of Temporal Point Processes](https://mlsanity.com/paper/1909.12127/) (2019)
- [Transformer Embeddings of Irregularly Spaced Events and Their Participants](https://mlsanity.com/paper/2201.00044/) (2021)
- [HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences](https://mlsanity.com/paper/2210.01753/) (2022)
- [Lecture Notes: Temporal Point Processes and the Conditional Intensity Function](https://mlsanity.com/paper/1806.00221/) (2018)
- [Fast and Flexible Temporal Point Processes with Triangular Maps](https://mlsanity.com/paper/2006.12631/) (2020)
- [Continuous Speculative Decoding for Autoregressive Image Generation](https://mlsanity.com/paper/2411.11925/) (2024)
- [Decomposable Transformer Point Processes](https://mlsanity.com/paper/2409.18158/) (2024)
- [Interpretable Transformer Hawkes Processes: Unveiling Complex Interactions in Social Networks](https://mlsanity.com/paper/2405.16059/) (2024)
- [TransFeat-TPP: An Interpretable Deep Covariate Temporal Point Processes](https://mlsanity.com/paper/2407.16161/) (2024)

## Built on by (most cited first, 3 of 3)

- [Make Every Draft Count: Hidden State based Speculative Decoding](https://mlsanity.com/paper/2602.21224/) (2026)
- [Accelerating Time Series Foundation Models with Speculative Decoding](https://mlsanity.com/paper/2511.18191/) (2025)
- [One Model, Multiple Compute Budgets: Multi-Ratio ConceptMoE for Flexible Compute Across Turns](https://mlsanity.com/paper/2610.14074/) (2026)

## Abstract (arXiv)

We propose TPP-SD, a novel approach that accelerates Transformer temporal point process (TPP) sampling by adapting speculative decoding (SD) techniques from language models. By identifying the structural similarities between thinning algorithms for TPPs and speculative decoding for language models, we develop an efficient sampling framework that leverages a smaller draft model to generate multiple candidate events, which are then verified by the larger target model in parallel. TPP-SD maintains the same output distribution as autoregressive sampling while achieving significant acceleration. Experiments on both synthetic and real datasets demonstrate that our approach produces samples from identical distributions as standard methods, but with 2-6× speedup. Our ablation studies analyze the impact of hyperparameters such as draft length and draft model size on sampling efficiency. TPP-SD bridges the gap between powerful Transformer TPP models and the practical need for rapid sequence sampling.