Metraipolis › archive › dc_9049fa4efe1a

A Spectral Theory of Compositional Learning — arXiv:2609.33708

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33708
License (as archived)
CC0-1.0
Archived
2026-10-07T22:37:42.593Z
SHA-256 of the archived text
18a4f9f4c8d18de79aeb886d3e18a502b08e47697666bc022e978cad56a9c331
Stable URL of this page
https://metraipolis.com/documento/dc_9049fa4efe1a

How to cite

A Spectral Theory of Compositional Learning — arXiv:2609.33708 — arXiv (en), https://arxiv.org/abs/2609.33708 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9049fa4efe1a (Metraipolis archive dc_9049fa4efe1a, sha256 18a4f9f4c8d18de79aeb886d3e18a502b08e47697666bc022e978cad56a9c331)
BibTeX
@misc{dc9049fa4efe1a,
  title = {A Spectral Theory of Compositional Learning — arXiv:2609.33708},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33708},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9049fa4efe1a; sha256 18a4f9f4c8d18de79aeb886d3e18a502b08e47697666bc022e978cad56a9c331},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33708. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

How does compositional reasoning emerge during learning? We address this question by mathematically analyzing the learning dynamics of deep linear networks. We train these networks in structured synthetic environments and derive a theory linking the structure of experience to compositional learning. Our theory predicts when compositional inferences emerge, whether they are identifiable from the available evidence, and how new linking evidence can rapidly unlock previously unavailable inferences. These results provide a qualitative explanation for several phenomena observed in human cognition. They account for why a composition can fail despite knowing its premises, why similar compositions can emerge at different times, and how a single linking fact can suddenly enable many new inferences. Taken together, these findings establish a mathematical link between the statistical structure of experience and the development of compositional reasoning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.33708 — 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 2026-10-07T22:14:28.022Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).