Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors

Abstract

This paper is an extended abstract of our ICLR 2024 Outstanding Paper Award work. Modeling long-range dependencies across sequences is a longstanding goal in machine learning. While state space models reportedly outperform Transformers on benchmarks like Long Range Arena, we show that random initialization significantly overestimates architectural differences. Pretraining with standard denoising objectives on downstream task data leads to dramatic gains across architectures and minimal performance gaps between Transformers and state space models (SSMs). We demonstrate that properly pretrained vanilla Transformers match S4 performance on Long Range Arena and improve SSM results on PathX-256 by 20 absolute points. Our analysis shows previously-proposed structured parameterizations for SSMs become largely redundant with pretraining. When evaluating architectures on supervised tasks, incorporating data-driven priors via pretraining is essential for reliable performance estimation.