TPP-SD: Accelerating Transformer Point Process Sampling with Speculative Decoding
This work addresses the practical need for faster sequence sampling in temporal point processes, which is incremental as it applies an existing technique to a new domain.
The paper tackled the problem of slow sampling in Transformer temporal point processes by adapting speculative decoding from language models, achieving a 2-6x speedup while maintaining identical output distributions.
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$\times$ 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.