Abstract:We prove lower bounds on learning the Möbius or Liouville function with a variety of standard learning techniques, including kernel methods, noisy gradient methods, and correlational statistical query algorithms. These results follow from quantitative bounds on the correlation of Möbius with digital characters of various finite abelian groups, where the group is dictated by the type of input data the algorithm is given. Using residues mod $p$ for many different primes corresponds to a cyclic group, and using the base $p$ expansion for a fixed prime corresponds to an elementary abelian $p$-group. We also note that lower bounds of this form are closely related to certain types of digital prime number theorems.
| Comments: | 62 pages |
| Subjects: | Number Theory (math.NT); Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.23427 [math.NT] |
| (or arXiv:2604.23427v1 [math.NT] for this version) | |
| https://doi.org/10.48550/arXiv.2604.23427 arXiv-issued DOI via DataCite (pending registration) |
From: Alexey Pozdnyakov [view email]
[v1]
Sat, 25 Apr 2026 19:43:06 UTC (53 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。