Sari la conținut

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

perspectiva aiqbenchMachine learning

analiza aiqbench

This note tightens a theoretical bound on list replicability, a measure of how consistently a learning algorithm can produce the same outputs across runs on fresh samples, when it may return a short list of candidates. A polylogarithmic upper bound would be a notable result, since it would show the quantity grows slowly with the number of concepts and domain points. The paper is a proof-simplification of a recent preprint not yet independently established, so readers should treat the result as a theoretical claim pending scrutiny rather than a practical guarantee.
Sursă care acoperăarXiv
Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

A polylogarithmic bound for list replicability

arXiv1 min de cititArticolul și perspectiva sunt în engleză.

arXiv:2610.20657v1 Announce Type: cross Abstract: Zhang [Zha26] recently posted a manuscript announcing that the list-replicability number of every class of $M\ge 2$ binary concepts on $N\ge 2$ domain points is $O(\log^2 M\log N)$, which would be the first polylogarithmic upper bound on this quantity. In this note, we present a short, self-contained proof of this bound, following the high-level approach of the manuscript but with considerably simpler arguments.

Abstract:Zhang [Zha26] recently posted a manuscript announcing that the list-replicability number of every class of $M\ge 2$ binary concepts on $N\ge 2$ domain points is $O(\log^2 M\log N)$, which would be the first polylogarithmic upper bound on this quantity. In this note, we present a short, self-contained proof of this bound, following the high-level approach of the manuscript but with considerably simpler arguments.

Machine Learning (stat.ML); Machine Learning (cs.LG); Combinatorics (math.CO)

arXiv:2610.20657 [stat.ML]

(or arXiv:2610.20657v1 [stat.ML] for this version)

https://doi.org/10.48550/arXiv.2610.20657 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Text integral sub licența deschisă a publicației · 160 cuvinte

Subiecte conexe