Skip to content
AI News HubLIVE
Original source3 min read

Layerwise Learning-Rate Scaling in Vision Networks: Effective-Rate Identification, Power-Mean Aggregation, and Budget Dependence

Summary

An arXiv paper shows that the rate-related effect of layerwise learning-rate strategies can be summarized by an effective learning rate computed directly from the multiplier profile. Test-accuracy changes closely track training-loss changes (r = -0.996), and a parameter-weighted power mean with exponent around 0.35 explains more within-architecture variance than the arithmetic mean. Ranking candidates by this scalar without training improves the selected candidate's mean percentile rank from 26th to 10th and cuts its accuracy shortfall from 3.70 to 1.12 points. The effect decays as training budgets grow.

SourcearXiv Machine LearningAuthor: Chandini Vysyaraju, Raghuvir Duvvuri, Radu Timofte, Dmitry Ignatov
Layerwise Learning-Rate Scaling in Vision Networks: Effective-Rate Identification, Power-Mean Aggregation, and Budget Dependence
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 16 Nov 2026]

Title:Layerwise Learning-Rate Scaling in Vision Networks: Effective-Rate Identification, Power-Mean Aggregation, and Budget Dependence

View a PDF of the paper titled Layerwise Learning-Rate Scaling in Vision Networks: Effective-Rate Identification, Power-Mean Aggregation, and Budget Dependence, by Chandini Vysyaraju and 3 other authors

View PDF HTML (experimental)

Abstract:Layerwise learning-rate scaling assigns different learning rates to different parts of a network. Although established in fine-tuning pretrained models, its effects in vision networks trained from scratch are commonly assessed by training each candidate recipe. We show that, in this setting, the rate-related component of a layerwise strategy is well summarized by an effective learning rate computable directly from its multiplier profile. Across matched-control comparisons, changes in test accuracy closely track changes in training loss (r = -0.996), which supports an optimization-progress explanation of the short-budget rate effect. Increasing the untuned base learning rate tenfold shifts the rate-matched contrast upward in all six tested architectures (p = 0.016) and increases the number of architectures in which a published discriminative schedule, excluded from model fitting, outperforms the uniform control from two to five of six (p = 0.031). Within the evaluated strategy space, a parameter-weighted power mean with exponent 0.35 (95% confidence interval [0.20, 0.50]) accounts for 42.6% of within-architecture variance, compared with 36.4% for the arithmetic mean. Ranking candidates by this scalar without training improves the selected candidate's mean percentile rank from the 26th to the 10th and reduces its mean accuracy shortfall relative to the best candidate from 3.70 to 1.12 points. The rate-related effect decays as the training budget increases; relative to tuned baselines, the overall strategy effect falls within the prespecified practical-equivalence margin in two of three architectures. A separate grouping-related contrast can persist at long budgets, although its direction and magnitude depend on the architecture.

Comments: 10 pages, 6 figures. Supplementary material (15 pages) included as an ancillary file. Data and analysis scripts: this https URL

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2611.21696 [cs.LG]

(or arXiv:2611.21696v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2611.21696

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Chandini Vysyaraju [view email] [v1] Mon, 16 Nov 2026 12:48:08 UTC (690 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Layerwise Learning-Rate Scaling in Vision Networks: Effective-Rate Identification, Power-Mean Aggregation, and Budget Dependence, by Chandini Vysyaraju and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Ancillary-file links:

Ancillary files (details):

supplementary.pdf

Additional Features

Audio Summary

Current browse context:

cs.LG

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

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

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 (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? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • The rate-related component of a layerwise strategy is summarized by an effective learning rate computed directly from its multiplier profile
  • Test-accuracy changes closely track training-loss changes (r = -0.996), supporting an optimization-progress explanation
  • A parameter-weighted power mean with exponent 0.35 (95% CI [0.20, 0.50]) explains 42.6% of within-architecture variance versus 36.4% for the arithmetic mean
  • Training-free ranking by this scalar lifts mean percentile rank from 26th to 10th and reduces accuracy shortfall from 3.70 to 1.12 points
  • The rate effect decays with larger budgets, falling within the practical-equivalence margin in two of three architectures

Highlights and analysis are generated automatically and may contain errors. Check the original source.