Metraipolis › archive › dc_588ee2002da2

Learning curves in natural and artificial systems — arXiv:2611.05224

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.05224
License (as archived): CC0-1.0
Archived: 2026-11-04T18:56:05.222Z
SHA-256 of the archived text: b464896c5f553fe324177ae790dc7d2ab6d21f706a84ed2131dcfeb43a7178ea
Stable URL of this page: https://metraipolis.com/documento/dc_588ee2002da2

How to cite

Learning curves in natural and artificial systems — arXiv:2611.05224 — arXiv (en), https://arxiv.org/abs/2611.05224 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_588ee2002da2 (Metraipolis archive dc_588ee2002da2, sha256 b464896c5f553fe324177ae790dc7d2ab6d21f706a84ed2131dcfeb43a7178ea)

BibTeX

@misc{dc588ee2002da2,
  title = {Learning curves in natural and artificial systems — arXiv:2611.05224},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05224},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_588ee2002da2; sha256 b464896c5f553fe324177ae790dc7d2ab6d21f706a84ed2131dcfeb43a7178ea},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05224. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A general mathematical model of experience formation is considered, in which the learning level is defined as the probability that the next value of the uncertainty factor has already been mastered and not forgotten. Within this model the shape of the learning curve is derived, and it turns out to be determined primarily by the distribution of situation occurrence: a uniform distribution yields an exponential curve, whereas a power-law distribution yields a power-law curve whose exponent equals the ratio of the distribution exponent to that same exponent increased by one. Both mechanisms generating power-law curves, established earlier in the analysis of debugging, assembly and repair activities, are shown to have been independently rediscovered in deep learning theory as the "frequency" and "spectral" mechanisms of scaling laws for artificial neural networks, while the exponential curves of machine learning (contraction operators, strongly convex optimization, stationary reinforcement) are generated by the same constancy of the contraction coefficient that was revealed half a century earlier in models of radioactive decay, the first-order lag element, and others. A solution is given for the problem of choosing a training distribution that differs from the deployment distribution. A methodological consequence is discussed: three distinct mechanisms generate curves indistinguishable in shape, so an observed learning curve does not allow one to judge the "internal" structure of the learning system.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Systems and Control (eess.SY) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.05224 — 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 2026-11-04T18:35:37.550Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).