Metraipolis › archive › dc_d4fa73c0e4a2

The Type-II Error of Test Supermartingales: e-Power versus the Chernoff-Stein Exponent — arXiv:2609.27765

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27765
License (as archived)
CC0-1.0
Archived
2026-10-08T10:58:07.403Z
SHA-256 of the archived text
5882f3d2c8ccf198f62d45a25a0d146caac87d887bdce89f8dda88e6eb38534a
Stable URL of this page
https://metraipolis.com/documento/dc_d4fa73c0e4a2

How to cite

The Type-II Error of Test Supermartingales: e-Power versus the Chernoff-Stein Exponent — arXiv:2609.27765 — arXiv (en), https://arxiv.org/abs/2609.27765 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d4fa73c0e4a2 (Metraipolis archive dc_d4fa73c0e4a2, sha256 5882f3d2c8ccf198f62d45a25a0d146caac87d887bdce89f8dda88e6eb38534a)
BibTeX
@misc{dcd4fa73c0e4a2,
  title = {The Type-II Error of Test Supermartingales: e-Power versus the Chernoff-Stein Exponent — arXiv:2609.27765},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27765},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d4fa73c0e4a2; sha256 5882f3d2c8ccf198f62d45a25a0d146caac87d887bdce89f8dda88e6eb38534a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27765. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In safe hypothesis testing with test supermartingales, 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 $1/\alpha$. Due to an inherent asymmetry, the type-II error behaves differently. We prove two things about the latter, for a simple null and alternative. First, the mean growth rate $\mathbb{E}_{P_1}[\log E]$, the e-power, that Kelly betting and growth-rate-optimal e-variables maximise, bounds nothing on its own. For every level $c>0$, every $\alpha$ and horizon $t$ we construct e-variables of conditional e-power exactly $c$ whose probability of not rejecting by $t$ is arbitrarily close to one. It forces eventual rejection, but no finite-horizon guarantee follows. Second, the quantity that does control the type-II error is the Chernoff-Stein exponent of an e-variable, $\Lambda(E)=\sup_{s\ge0}\{-\log \mathbb{E}_{P_1}[E^{-s}]\}$, whose range is exactly determined: $\sup_E \Lambda(E)=\mathrm{KL}(P_0\|P_1)$, the classical Chernoff-Stein exponent, and so the ceiling of its own per-e-variable form. One conditional application of Hoelder's inequality per step gives it, for every test supermartingale on an arbitrary filtered space, with no independence or product structure; the i.i.d. case adds that it is matched, and attained by nothing. The e-power has its own ceiling, $\mathrm{KL}(P_1\|P_0)$, and that one is attained, $P_0$-a.s. uniquely, by the likelihood ratio $R$. The two optima are the same divergence in opposite arguments, at opposite ends of the flattened family $R^{\beta}/\mathbb{E}_{P_0}[R^{\beta}]$: the ceiling as $\beta\downarrow0$, $R$ at $\beta=1$. Which $\beta$ is best is settled by the horizon, exactly: $R$ is optimal at $t=\log(1/\alpha)/\mathrm{KL}(P_1\|P_0)$ alone, beaten by sharpening $(\beta>1)$ below it and by flattening above.

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/2609.27765 — 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 2026-10-08T10:06:16.823Z 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).