arXiv:2606.04048v1 Announce Type: cross
Abstract: Training and scaling Large Language Models demand enormous computational resources, motivating both efficient sub-quadratic architectures and principled hyperparameter tuning methods. While the Maximal Update Parametrization ($mu$P) has enabled zero-shot hyperparameter transfer for standard Transformers, its extension to linear models, particularly those with structured state transitions and complicated architectures, remains largely unexplored. By rigorously propagating coordinate-size estimates through the forward pass, gating mechanisms, and recurrent state dynamics, we derive the scaling rules for Gated Delta Network. Experiments on language-model pre-training confirm that our configurations enable stable learning-rate transfer across model widths under both AdamW and SGD, whereas standard parametrization fails to transfer, validating the correctness and practical utility of our analysis.

Subscribe for Updates

Copyright 2025 dijee Intelligence Ltd.   dijee Intelligence Ltd. is a private limited company registered in England and Wales at Media House, Sopers Road, Cuffley, Hertfordshire, EN6 4RY, UK registration number 16808844