The Serial Scaling Hypothesis

ICLR 2026 Conference Submission16035 Authors

Keywords: Scaling Law, Computation complexity

TL;DR: Serial scaling is just as important as parallel scaling in machine learning, though it has been undeservedly neglected.

Abstract: While machine learning has advanced through massive parallelization, we identify a critical blind spot: some problems are fundamentally sequential. These "inherently serial" problems—from mathematical reasoning to physical simulations to sequential decision-making—require sequentially dependent computational steps that cannot be efficiently parallelized. We formalize this distinction in complexity theory, and demonstrate that current parallel-centric architectures face fundamental limitations on such tasks. Then, we show for first time that diffusion models despite their sequential nature are incapable of solving inherently serial problems. We argue that recognizing the serial nature of computation holds profound implications on machine learning, model design, and hardware development.

Primary Area: learning theory

Submission Number: 16035