2026-06-04原文2 min readUpdated: 2026-06-04

Unlocking Feature Learning in Gated Delta Networks at Scale

This paper extends the Maximal Update Parametrization (μP) to Gated Delta Networks, an efficient linear architecture. By rigorously propagating coordinate-size estimates through the forward pass, gating mechanisms, and recurrent state dynamics, the authors derive scaling rules that enable stable learning-rate transfer across model widths under AdamW and SGD, whereas standard parametrization fails.

SourcearXiv Machine LearningAuthor: Yifeng Liu, Quanquan Gu

[2606.04048] Unlocking Feature Learning in Gated Delta Networks at Scale

[Submitted on 2 Jun 2026]

Title:Unlocking Feature Learning in Gated Delta Networks at Scale

View a PDF of the paper titled Unlocking Feature Learning in Gated Delta Networks at Scale, by Yifeng Liu and Quanquan Gu

View PDF HTML (experimental)

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.

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

Cite as: arXiv:2606.04048 [cs.LG]

(or arXiv:2606.04048v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2606.04048

arXiv-issued DOI via DataCite

Submission history

From: Yifeng Liu [view email] [v1] Tue, 2 Jun 2026 08:45:24 UTC (240 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Unlocking Feature Learning in Gated Delta Networks at Scale, by Yifeng Liu and Quanquan Gu

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-06

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)