Metraipolis › archive › dc_75499ce52ddd
SaMA: Morpho Adaptation via Asymmetric Expansion of Kronecker Product — arXiv:2611.04462
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04462
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T21:40:03.093Z
- SHA-256 of the archived text
b12ba0e4f7bb314949518d8b5edfd9f12402dacbddef80b15c80aa00fb7780c5- Stable URL of this page
https://metraipolis.com/documento/dc_75499ce52ddd
How to cite
SaMA: Morpho Adaptation via Asymmetric Expansion of Kronecker Product — arXiv:2611.04462 — arXiv (en), https://arxiv.org/abs/2611.04462 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_75499ce52ddd (Metraipolis archive dc_75499ce52ddd, sha256 b12ba0e4f7bb314949518d8b5edfd9f12402dacbddef80b15c80aa00fb7780c5)
BibTeX
@misc{dc75499ce52ddd,
title = {SaMA: Morpho Adaptation via Asymmetric Expansion of Kronecker Product — arXiv:2611.04462},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04462},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_75499ce52ddd; sha256 b12ba0e4f7bb314949518d8b5edfd9f12402dacbddef80b15c80aa00fb7780c5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04462. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Low-rank adaptation (LoRA) has attracted significant attention in the parameter-efficient fine-tuning (PEFT) landscape. However, its design suffers from two fundamental limitations. First, its invariance manifold induces flat directions in the loss landscape, creating an optimization bottleneck for adaptive optimizers. Second, its effective rank scales only linearly with the parameter budget. In this paper, we propose Scalable Morpho Adaptation (SaMA), a PEFT method grounded in a principled generalization of the Kronecker product. By relaxing the shared-block constraint in the perfect-shuffle factorization, SaMA spans from low to full rank and achieves a practical rank that scales quadratically with the parameter budget, up to full-rank. Furthermore, we show that its invariance manifold collapses to a diagonal group, making it structurally more optimizer-friendly. Empirically, SaMA consistently outperforms strong PEFT baselines on commonsense and arithmetic reasoning benchmarks while being more parameter-efficient. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.04462 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-04T21:35:49.671Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).