Papers/2611.21696
🧪 Test?View on arXiv

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

Not provided in the abstract

fine-tuninglearning ratevision networks
2611.21696
Builder Relevance
70%
15h ago

Abstract

The paper explores layerwise learning-rate scaling in vision networks, demonstrating that an effective learning rate can be computed from its multiplier profile and significantly impacts training outcomes.

Reality Card

Core Claim

Layerwise learning-rate scaling can improve model selection and training efficiency, with a parameter-weighted power mean accounting for 42.6% of variance in architecture performance.

Method / Result

Ranking candidates by the scalar improved the mean percentile rank from the 26th to the 10th.

Limitations

The effectiveness of the proposed method may vary significantly across different architectures and training budgets.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers