Metraipolis › archive › dc_df0149df1a62
Understanding Generalization Requires Universal Induction — arXiv:2609.34458
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34458
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:02:37.222Z
- SHA-256 of the archived text
b54b32b7c14bd6a371e7cbd0e0cf92bdb97b1a8726a33ba837f2d86156428c06- Stable URL of this page
https://metraipolis.com/documento/dc_df0149df1a62
How to cite
Understanding Generalization Requires Universal Induction — arXiv:2609.34458 — arXiv (en), https://arxiv.org/abs/2609.34458 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df0149df1a62 (Metraipolis archive dc_df0149df1a62, sha256 b54b32b7c14bd6a371e7cbd0e0cf92bdb97b1a8726a33ba837f2d86156428c06)
BibTeX
@misc{dcdf0149df1a62,
title = {Understanding Generalization Requires Universal Induction — arXiv:2609.34458},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34458},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df0149df1a62; sha256 b54b32b7c14bd6a371e7cbd0e0cf92bdb97b1a8726a33ba837f2d86156428c06},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34458. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Classical statistical theory is insufficient to explain the successes of general-purpose AI models, because it depends on handcrafted inductive biases that it cannot justify. No Free Lunch (NFL) theorems force any learner that beats chance on some environments to underperform on others. We might hope that past experience informs which environments to expect, but NFL applies equally to meta-learning. Thus, any method that makes meaningful predictions necessarily begins with an inductive bias external to the data. Choosing to bias toward short programs yields Solomonoff induction (SI), whose performance is competitive against all computable learners - albeit up to "constants" that become large when comparing against specialized methods that exploit background information. We therefore relativize SI to an information vantage point, biasing toward short programs with access to all preexisting information. This reframes the inductive bias: instead of seeking some absolute notion of simplicity, we favor accessibility with respect to our vantage point. An algorithm can only outpredict the relativized SI to the extent that its code contains additional information about the data, and no algorithm can generate such information. While SI is incomputable and hence not a practical algorithm, it provides a formal optimum for inference in the limit of infinite compute, and there is evidence to suggest that frontier AI systems roughly approximate it. Thus, the only known answer to meta-NFL is rooted in algorithmic information theory, which we should expect to play a fundamental role in explaining the generalization behavior of modern (and future) AI systems. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Machine Learning (stat.ML) ; Artificial Intelligence (cs.AI); Information Theory (cs.IT); Machine Learning (cs.LG); Statistics Theory (math.ST). Pagina del lavoro: https://arxiv.org/abs/2609.34458 — 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 2026-10-07T20:29:03.001Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).