PULSELoCo: 17x less trainer-to-trainer bandwidth in distributed RL post-training

synapz_org1 pts0 comments

[2602.03839] Understanding and Exploiting Weight Update Sparsity for Communication-Efficient Distributed RL

-->

Computer Science > Machine Learning

arXiv:2602.03839 (cs)

[Submitted on 3 Feb 2026 (v1), last revised 19 May 2026 (this version, v2)]

Title:Understanding and Exploiting Weight Update Sparsity for Communication-Efficient Distributed RL

Authors:Erfan Miahi, Eugene Belilovsky<br>View a PDF of the paper titled Understanding and Exploiting Weight Update Sparsity for Communication-Efficient Distributed RL, by Erfan Miahi and 1 other authors

View PDF<br>HTML (experimental)

Abstract:Bandwidth-constrained distributed reinforcement learning (RL) post-training of large language models is bottlenecked by two channels: weight synchronization from trainers to inference workers, and gradient or pseudo-gradient synchronization across trainers. We find that approximately 99% of per-step weight updates are invisible after the BF16 cast used by standard training and inference forward passes. We explain this sparsity by showing that, at typical RL post-training learning rates, Adam updates often fall below the local BF16 rounding threshold. We turn this observation into an algorithmic principle called compute-visible sparsification: transmit only updates that would change the next forward pass. PULSE (Precision-gated Updates for Low-precision Sparse Exchange) turns this principle into two communication algorithms: PULSESync sends lossless sparse BF16 weight patches from trainers to inference workers, and PULSELoCo sparsifies DiLoCo-style FP32 pseudo-gradient synchronization with error feedback. Over bandwidth-constrained commodity networks, PULSESync cuts weight-synchronization communication by over 100x while reconstructing trainer weights bit-identically. PULSELoCo matches DiLoCo across four models while reducing trainer-to-trainer communication by over 17x versus DiLoCo and over 100x versus DDP in the largest evaluated setting.

Comments:<br>40 pages, 19 figures, 14 tables

Subjects:

Machine Learning (cs.LG)

Cite as:<br>arXiv:2602.03839 [cs.LG]

(or<br>arXiv:2602.03839v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2602.03839

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Erfan Miahi [view email]<br>[v1]<br>Tue, 3 Feb 2026 18:56:48 UTC (527 KB)

[v2]<br>Tue, 19 May 2026 16:03:06 UTC (1,001 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Understanding and Exploiting Weight Update Sparsity for Communication-Efficient Distributed RL, by Erfan Miahi and 1 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.LG

next >

new<br>recent<br>| 2026-02

Change to browse by:

cs

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

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

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender<br>(What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)

toggle weight arxiv communication distributed view

Related Articles