Overcoming Joint Intractability with Lossless Hierarchical Speculative Decoding

ICLR 2026 Conference Submission16354 Authors

Keywords: Speculative Decoding, Joint Intractability, Lossless Verification

Abstract: Verification is a key bottleneck in improving inference speed while maintaining distribution fidelity in Speculative Decoding. Recent work has shown that sequence-level verification leads to a higher number of accepted tokens compared to token-wise verification. However, existing solutions often rely on surrogate approximations or are constrained by partial information, struggling with joint intractability. In this work, we propose Hierarchical Speculative Decoding (HSD), a provably lossless verification method that significantly boosts the expected number of accepted tokens and overcomes joint intractability by balancing excess and deficient mass across accessible branches. Through extensive large-scale experiments, we show that HSD consistently improves acceptance rates, especially with longer draft sequences. Its strong explainability and generality further highlight the potential for integration into a wide range of speculative decoding frameworks.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 16354