Metraipolis › archive › dc_bf4796486a07
Solvable dynamics model of in-context learning — arXiv:2611.00921
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00921
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:20:49.996Z
- SHA-256 of the archived text
3634fb0278354910d916b1747c8735caa5695cdab80bb42a932b5f88973936af- Stable URL of this page
https://metraipolis.com/documento/dc_bf4796486a07
How to cite
Solvable dynamics model of in-context learning — arXiv:2611.00921 — arXiv (en), https://arxiv.org/abs/2611.00921 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf4796486a07 (Metraipolis archive dc_bf4796486a07, sha256 3634fb0278354910d916b1747c8735caa5695cdab80bb42a932b5f88973936af)
BibTeX
@misc{dcbf4796486a07,
title = {Solvable dynamics model of in-context learning — arXiv:2611.00921},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00921},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf4796486a07; sha256 3634fb0278354910d916b1747c8735caa5695cdab80bb42a932b5f88973936af},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00921. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Pretrained Transformer architectures display a surprising in-context learning ability without additional training. How the learning process guides the network to achieve this intriguing capability remains unsolved. In this study, we focus on a single-layer, single-head linear attention model, where empirical risk minimization is defined for learning. Given a finite amount of training examples, we determine the exact solution of network parameter dynamics, which is linked to the training error and generalization error, characterizing how memorization and generalization emerge from learning and how these transitions are related to curvatures of the empirical risk landscape. Furthermore, we calculate a data-dependent free energy, from which the training and generalization errors in the long-time limit of learning dynamics can be well predicted. Our work adds insights toward understanding the mechanism of in-context learning, especially from a learning dynamics perspective. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Disordered Systems and Neural Networks (cond-mat.dis-nn). Pagina del lavoro: https://arxiv.org/abs/2611.00921 — 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 2026-11-03T11:02:37.485Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).