Uniform Scaling Limits in AdamW-Trained Transformers
arXiv 2605.11059•a775b843fcf21f97a1c9372b9896377eee142f4e405924453db1e315f5d10a2f
ADMMAdamWBayesian-KANsGaussian-processGibbs-samplingLie-algebraMcKean-VlasovSO(3)Stiefel-optimizationThompson-samplingU-statisticsactive-inferenceadaptive-experimentationattention-mechanismlow-rank-covariancenetwork-interferencepost-ADC-inferenceprobabilistic-PLSrotational-anisotropyscaling-limitsselective-inferencespatial-adapterspectral-distillationtransformerstree-ensembles
Paper metadata
- arXiv ID
- 2605.11059
- Version
- Not specified by this published record
- Category
- Statistics — Machine Learning (stat.ML)
The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.
Evidence and limitations
- Source ID
- arxiv_stat_ml
- Record identifier
- a775b843fcf21f97a1c9372b9896377eee142f4e405924453db1e315f5d10a2f
- Enrichment time
- 2026-05-13T07:23:57Z
- AI-assisted enrichment
- Yes
This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.