Metraipolis › archive › dc_dddf7f15ceed

LIRA: A More Interpretable Dynamic Loss-Informed Rank Allocation for Low-Rank Adaptation — arXiv:2611.04239

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.04239
License (as archived): CC0-1.0
Archived: 2026-11-04T18:36:32.678Z
SHA-256 of the archived text: 93ae7e26682b92a966b339e4f4f0c2e34e931cd6cb87e712e2cd49974aca6ec8
Stable URL of this page: https://metraipolis.com/documento/dc_dddf7f15ceed

How to cite

LIRA: A More Interpretable Dynamic Loss-Informed Rank Allocation for Low-Rank Adaptation — arXiv:2611.04239 — arXiv (en), https://arxiv.org/abs/2611.04239 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dddf7f15ceed (Metraipolis archive dc_dddf7f15ceed, sha256 93ae7e26682b92a966b339e4f4f0c2e34e931cd6cb87e712e2cd49974aca6ec8)

BibTeX

@misc{dcdddf7f15ceed,
  title = {LIRA: A More Interpretable Dynamic Loss-Informed Rank Allocation for Low-Rank Adaptation — arXiv:2611.04239},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04239},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dddf7f15ceed; sha256 93ae7e26682b92a966b339e4f4f0c2e34e931cd6cb87e712e2cd49974aca6ec8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04239. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Low-rank adaptation (LoRA) has become a widely used parameter-efficient fine-tuning method for large pretrained models. However, standard LoRA typically assigns a fixed rank profile despite layer- and stage-dependent adaptation needs, while recent adaptive-rank variants often rely on heuristic or first-order signals that provide only an indirect link between rank reallocation and local loss behavior. This leaves the rationale behind each rank reallocation insufficiently interpretable. Motivated by this gap, we propose LIRA (Loss-Informed Rank Allocation), a dynamic-rank LoRA method designed to make online rank reallocation more interpretable. LIRA scores each layer by the estimated magnitude of the local loss perturbation associated with its recent LoRA-factor movements under a second-order approximation, making the basis for each rank change interpretable term by term. By periodically applying DELTA (Displacement-Evaluated Loss-Trajectory Allocation), a displacement-based algorithm for LoRA rank reallocation, LIRA produces discrete effective ranks under matched budgets while remaining compatible with standard (A,B) adapters. On RoBERTa-base GLUE under the La-LoRA/LoRA protocol, LIRA outperforms the uniform-LoRA and adaptive-rank baselines reported under this protocol; Trajectory EMA attains performance competitive with Fixed-point Fisher at lower estimation cost.

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/2611.04239 — 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 2026-11-04T18:32:37.427Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).