Metraipolis › archive › dc_bf446679faad

Type-II Error Bounds for Test Supermartingales from Lower-Tail Hypotheses — arXiv:2609.27766

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27766
License (as archived)
CC0-1.0
Archived
2026-10-08T10:58:08.261Z
SHA-256 of the archived text
11ea89d7107a2d201e009a8ed7f906df9ebca93008285023d8798c3ab3e356e7
Stable URL of this page
https://metraipolis.com/documento/dc_bf446679faad

How to cite

Type-II Error Bounds for Test Supermartingales from Lower-Tail Hypotheses — arXiv:2609.27766 — arXiv (en), https://arxiv.org/abs/2609.27766 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf446679faad (Metraipolis archive dc_bf446679faad, sha256 11ea89d7107a2d201e009a8ed7f906df9ebca93008285023d8798c3ab3e356e7)
BibTeX
@misc{dcbf446679faad,
  title = {Type-II Error Bounds for Test Supermartingales from Lower-Tail Hypotheses — arXiv:2609.27766},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27766},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf446679faad; sha256 11ea89d7107a2d201e009a8ed7f906df9ebca93008285023d8798c3ab3e356e7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27766. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In safe hypothesis testing with test supermartingals, Ville's inequality provides anytime-valid type-I error guarantees for every significance level $\alpha\in(0,1]$, if one rejects the null hypothesis whenever the wealth process first exceeds $\frac{1}{\alpha}$. Due to an inherent asymmetry, the type-II error does not have such guarantees: a heavy concentration of the probability on the lower tail of the log-increments can lead to one catastrophic bet that undoes any amount of accumulated evidence. This paper studies how different hypotheses on those lower-tail probabilities lead to different bounds on the type-II error of the sequential test. They all reduce to one master inequality, which bounds the type-II error at level $\alpha$, at a fixed horizon and sequentially, in terms of a one-sided Legendre transform of the (inverse-)moment generating function of the e-variables, evaluated at one number: the amount by which the lower bound of the accumulated e-powers exceeds $\log\frac{1}{\alpha}$. And, the step is lossless, in the sense, that it extracts exactly a constrained information projection. Every bound presented here is a corollary, obtained by a certain majorant of the above function. The hypotheses are: a finite negative moment; an exponentially small crash probability with a moment on the winning side; a wealth floor with a conditional variance, and its Bernstein variant, which interpolates between a Gaussian regime set by the variance and an exponential one set by the scale; a sub-Gaussian or bounded-tilt lower tail; bounded log-increments; and i.i.d. increments, where the majorant is the truth. We also provide an empirical-Bernstein variant. Each hypothesis may either be read as a condition on the e-variables one has, or as the price of betting with an approximation to the likelihood ratio rather than the ratio itself, which satisfies the weakest condition for free.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.LG).
Categorie arXiv: Statistics Theory (math.ST) ; Information Theory (cs.IT); Machine Learning (cs.LG); Probability (math.PR); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.27766 — 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 2026-10-08T10:06:16.824Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).