paper-with-me

홈 › Papers

Studying number theory with deep learning: a case study with the Möbius and squarefree indicator functions

2025-02-14 · David Lowry-Duda

Building on work of Charton, we train small transformer models to calculate the M\"obius function $\mu(n)$ and the squarefree indicator function $\mu^2(n)$. The models attain nontrivial predictive power. We then iteratively train additional models to understand how the model functions, ultimately finding a theoretical explanation.

📄 PDF Abstract BibTeX arXiv:2502.10335

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The Weighted Möbius Score: A Unified Framework for Feature Attribution

2023-05-16 · Yifan Jiang, Shane Steinert-Threlkeld

Feature attribution aims to explain the reasoning behind a black-box model's prediction by identifying the impact of each feature on the prediction. Recent work has extended feature attribution to interactions between mu…

Sentiment Analysis

Computational Aspects of the Mobius Transform

2013-03-27 · Robert Kennes, Philippe Smets

In this paper we associate with every (directed) graph G a transformation called the Mobius transformation of the graph G. The Mobius transformation of the graph (O) is of major significance for Dempster-Shafer theory of…

Imbalance Prime Sieving: Every Prime Gap Is a Result of a Möbius Imbalance Obstruction

2025-07-01 · SSRN 2025 7 · Paul Alexander Bilokon

We introduce a novel sieve for prime numbers based on detecting topological obstructions in a Möbius-transformed rational metric space. Unlike traditional sieves which rely on divisibility, our method identifies primes a…

Learning to Understand: Identifying Interactions via the Möbius Transform

2024-02-04 · Justin S. Kang, Yigit E. Erginbas, Landon Butler, Ramtin Pedarsani 외

One of the key challenges in machine learning is to find interpretable representations of learned functions. The M\"obius transform is essential for this purpose, as its coefficients correspond to unique importance score…

Learning Theory

Free resolutions of function classes via order complexes

2019-09-05 · Justin Chen, Christopher Eur, Greg Yang, Mengyuan Zhang

Function classes are collections of Boolean functions on a finite set, which are fundamental objects of study in theoretical computer science. We study algebraic properties of ideals associated to function classes previo…

Learning Theory