Metraipolis › archive › dc_ab943b65bf5d

Solomonoff Induction and Singular Integrals — arXiv:2609.01666

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01666
License (as archived)
CC0-1.0
Archived
2026-10-17T05:45:35.517Z
SHA-256 of the archived text
65390c1c66d5a6ce6824f24691785e00c3712247bbec1ec283fad4e23dd0feeb
Stable URL of this page
https://metraipolis.com/documento/dc_ab943b65bf5d

How to cite

Solomonoff Induction and Singular Integrals — arXiv:2609.01666 — arXiv (en), https://arxiv.org/abs/2609.01666 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ab943b65bf5d (Metraipolis archive dc_ab943b65bf5d, sha256 65390c1c66d5a6ce6824f24691785e00c3712247bbec1ec283fad4e23dd0feeb)
BibTeX
@misc{dcab943b65bf5d,
  title = {Solomonoff Induction and Singular Integrals — arXiv:2609.01666},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01666},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ab943b65bf5d; sha256 65390c1c66d5a6ce6824f24691785e00c3712247bbec1ec283fad4e23dd0feeb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01666. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The Solomonoff distribution $M$ assigns an a priori probability to a finite binary string $z$ by summing over all programs whose output begins with $z$, weighting a program of length $\ell$ by $2^{-\ell}$. Thus, likely strings are those with many short explanations. This appears to be a purely discrete notion of complexity. However, Riemann sums are also countable. We show that the sum defining $M$, suitably reorganised, contains Riemann sums approximating the Bayesian evidence of any computable statistical model. These evidence integrals are singular integrals whose asymptotics are governed by Singular Learning Theory and, through it, by invariants of algebraic geometry. Concretely, for every computable Bayesian model, we construct a single monotone Turing machine whose induced semimeasure agrees with the evidence $Z_n$ up to a uniform multiplicative constant. If the model also satisfies the hypotheses of Watanabe's free-energy asymptotics, then a sample $X^n=X_1\cdots X_n$ drawn i.i.d. from the true distribution satisfies $-\log M(X^n) \le nL_n(w_0)+\lambda\log n-(m-1)\log\log n+O_{\mathbb{P}}(1)$, where $L_n$ is the empirical loss, $w_0$ is an optimal parameter, $\lambda$ is the learning coefficient, and $m$ is its multiplicity. Thus the learning coefficient, a geometric measure of model simplicity, appears within the Solomonoff distribution as the coefficient of $\log n$ in an upper bound on code length.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-03 in math.IT).
Categorie arXiv: Information Theory (cs.IT).
Pagina del lavoro: https://arxiv.org/abs/2609.01666 — 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 2026-10-17T05:17:18.087Z dalla pagina https://arxiv.org/catchup/math.IT/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).