From Black Box to Bijection: Interpreting Machine Learning to Build a Zeta Map Algorithm

• URL: http://arxiv.org/abs/2511.12421v1
• Date: Sun, 16 Nov 2025 02:17:37 GMT
• Title: From Black Box to Bijection: Interpreting Machine Learning to Build a Zeta Map Algorithm
• Abstract summary: We propose a new workflow for discovering explicit bijections via machine learning.<n>As a proof of concept, we train a transformer on paired Dyck paths and use its learned attention patterns to derive a new algorithmic description of the zeta map.
• Score: 2.3895981099137535
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: There is a large class of problems in algebraic combinatorics which can be distilled into the same challenge: construct an explicit combinatorial bijection. Traditionally, researchers have solved challenges like these by visually inspecting the data for patterns, formulating conjectures, and then proving them. But what is to be done if patterns fail to emerge until the data grows beyond human scale? In this paper, we propose a new workflow for discovering combinatorial bijections via machine learning. As a proof of concept, we train a transformer on paired Dyck paths and use its learned attention patterns to derive a new algorithmic description of the zeta map, which we call the \textit{Scaffolding Map}.

Related papers

• Discovering a Zeta Map Algorithm on Dyck Paths via Mechanistic Interpretability [2.3895981099137535]
  We train a small one-layer, one-head encoder-decoder transformer on a map of Dyck paths.<n>We analyze its learned using mechanistic interpretability tools, including decoder cross-attention analysis.<n>We prove that this algorithm agrees with the zeta map, modulo a reversal convention in the labeling.
  arXiv  Detail & Related papers  (2026-05-28T18:59:30Z)
• Mapping Uncharted Symmetries: Machine Discovery in Combinatorics [38.59031747973091]
  We show that modern machine learning can meaningfully contribute to verifiable mathematical discoveries.<n>In particular, we focus on the construction of simple mathematical functions under exact distributional constraints.<n>We find a new interpretation of $q,t$-Narayanas arising from representation theory.
  arXiv  Detail & Related papers  (2026-05-18T19:36:08Z)
• Can Neural Networks Learn Small Algebraic Worlds? An Investigation Into the Group-theoretic Structures Learned By Narrow Models Trained To Predict Group Operations [4.635620949885696]
  We explore the extent to which narrow models trained to solve a fixed mathematical task learn broader mathematical structure that can be extracted by a researcher or other AI system.<n>We describe a suite of tests designed to assess whether the model captures significant group-theoretic notions such as the identity element, commutativity, or subgroups.<n>Our results suggest that in some cases the representations of even small neural networks can be used to distill interesting abstract structure from new mathematical objects.
  arXiv  Detail & Related papers  (2026-01-29T01:18:22Z)
• Learning the symmetric group: large from small [41.99844472131922]
  We show that a transformer neural-network trained on predicting permutations can generalize to the symmetric group $S_25$ with near 100% accuracy.<n>We employ identity augmentation as a key tool to manage variable word lengths, and partitioned windows for training on adjacent transpositions.
  arXiv  Detail & Related papers  (2025-02-18T10:28:25Z)
• Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning [85.635988711588]
  We argue that enhancing the capabilities of large language models requires a paradigm shift in the design of mathematical datasets.<n>We advocate for mathematical dataset developers to consider the concept of "motivated proof", introduced by G. P'olya in 1949, which can serve as a blueprint for datasets that offer a better proof learning signal.<n>We provide a questionnaire designed specifically for math datasets that we urge creators to include with their datasets.
  arXiv  Detail & Related papers  (2024-12-19T18:55:17Z)
• Machines and Mathematical Mutations: Using GNNs to Characterize Quiver Mutation Classes [4.229995708813431]
  We use graph neural networks to investigate emphquiver mutation -- an operation that transforms one quiver into another.<n>In the study of cluster algebras, the question of emphmutation equivalence is of fundamental concern.<n>We show that our model captures structure within its hidden representation that allows us to reconstruct known criteria from type $D$.
  arXiv  Detail & Related papers  (2024-11-12T01:09:41Z)
• Disentangled Representation Learning with the Gromov-Monge Gap [65.73194652234848]
  Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning.<n>We introduce a novel approach to disentangled representation learning based on quadratic optimal transport.<n>We demonstrate the effectiveness of our approach for quantifying disentanglement across four standard benchmarks.
  arXiv  Detail & Related papers  (2024-07-10T16:51:32Z)
• Quantum One-Wayness of the Single-Round Sponge with Invertible Permutations [49.1574468325115]
  Sponge hashing is a widely used class of cryptographic hash algorithms.<n>Intrepid permutations have so far remained a fundamental open problem.<n>We show that finding zero-pairs in a random $2n$-bit permutation requires at least $Omega (2n/2)$ many queries.
  arXiv  Detail & Related papers  (2024-03-07T18:46:58Z)
• Unsupervised Learning of Invariance Transformations [105.54048699217668]
  We develop an algorithmic framework for finding approximate graph automorphisms. We discuss how this framework can be used to find approximate automorphisms in weighted graphs in general.
  arXiv  Detail & Related papers  (2023-07-24T17:03:28Z)
• What learning algorithm is in-context learning? Investigations with linear models [87.91612418166464]
  We investigate the hypothesis that transformer-based in-context learners implement standard learning algorithms implicitly. We show that trained in-context learners closely match the predictors computed by gradient descent, ridge regression, and exact least-squares regression. Preliminary evidence that in-context learners share algorithmic features with these predictors.
  arXiv  Detail & Related papers  (2022-11-28T18:59:51Z)
• Arbitrarily Large Labelled Random Satisfiability Formulas for Machine Learning Training [5.414308305392762]
  We show how to generate correctly labeled random formulas of any desired size without having to solve the underlying decision problem. We train existing state-of-the-art models for the task of predicting satisfiability on formulas with 10,000 variables. We find that they do no better than random guessing 99% on the same datasets.
  arXiv  Detail & Related papers  (2022-11-21T17:52:13Z)
• Heterogeneous Line Graph Transformer for Math Word Problems [21.4761673982334]
  This paper describes the design and implementation of a new machine learning model for online learning systems. We aim at improving the intelligent level of the systems by enabling an automated math word problem solver.
  arXiv  Detail & Related papers  (2022-08-11T05:27:05Z)
• Monotone Learning [86.77705135626186]
  We show that every learning algorithm A can be transformed to a monotone class with similar performance. This demonstrates that one can provably avoid non-monotonic behaviour without compromising performance.
  arXiv  Detail & Related papers  (2022-02-10T18:51:57Z)
• Reinforcement Explanation Learning [4.852320309766702]
  Black-box methods to generate saliency maps are particularly interesting due to the fact that they do not utilize the internals of the model to explain the decision. We formulate saliency map generation as a sequential search problem and leverage upon Reinforcement Learning (RL) to accumulate evidence from input images. Experiments on three benchmark datasets demonstrate the superiority of the proposed approach in inference time over state-of-the-arts without hurting the performance.
  arXiv  Detail & Related papers  (2021-11-26T10:20:01Z)
• Machine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoning [95.18337034090648]
  We propose a dataset, Machine Number Sense (MNS), consisting of visual arithmetic problems automatically generated using a grammar model--And-Or Graph (AOG) These visual arithmetic problems are in the form of geometric figures. We benchmark the MNS dataset using four predominant neural network models as baselines in this visual reasoning task.
  arXiv  Detail & Related papers  (2020-04-25T17:14:58Z)
• The data-driven physical-based equations discovery using evolutionary approach [77.34726150561087]
  We describe the algorithm for the mathematical equations discovery from the given observations data. The algorithm combines genetic programming with the sparse regression. It could be used for governing analytical equation discovery as well as for partial differential equations (PDE) discovery.
  arXiv  Detail & Related papers  (2020-04-03T17:21:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.