Generative Modeling for Mathematical Discovery

• URL: http://arxiv.org/abs/2503.11061v2
• Date: Mon, 17 Mar 2025 01:42:26 GMT
• Title: Generative Modeling for Mathematical Discovery
• Authors: Jordan S. Ellenberg, Cristofero S. Fraser-Taliente, Thomas R. Harvey, Karan Srivastava, Andrew V. Sutherland,
• Abstract summary: We present a new implementation of the genetic algorithm it funsearch.<n>Our aim is to generate examples of interest to mathematicians.<n>It does not require expertise in machine learning or access to high-performance computing resources.
• Score: 0.19791587637442667
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a new implementation of the LLM-driven genetic algorithm {\it funsearch}, whose aim is to generate examples of interest to mathematicians and which has already had some success in problems in extremal combinatorics. Our implementation is designed to be useful in practice for working mathematicians; it does not require expertise in machine learning or access to high-performance computing resources. Applying {\it funsearch} to a new problem involves modifying a small segment of Python code and selecting a large language model (LLM) from one of many third-party providers. We benchmarked our implementation on three different problems, obtaining metrics that may inform applications of {\it funsearch} to new problems. Our results demonstrate that {\it funsearch} successfully learns in a variety of combinatorial and number-theoretic settings, and in some contexts learns principles that generalize beyond the problem originally trained on.

Related papers

• Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics [4.229995708813431]
  We introduce a new collection of datasets, the Algebraic Combinatorics dataset Repository (ACD Repo)<n>Each dataset includes an open-ended research-level question and a large collection of examples.<n>We describe all nine datasets, the different ways machine learning models can be applied to them.
  arXiv  Detail & Related papers  (2025-03-09T00:11:40Z)
• From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models [63.188607839223046]
  This survey focuses on the benefits of scaling compute during inference. We explore three areas under a unified mathematical formalism: token-level generation algorithms, meta-generation algorithms, and efficient generation.
  arXiv  Detail & Related papers  (2024-06-24T17:45:59Z)
• Mathify: Evaluating Large Language Models on Mathematical Problem Solving Tasks [34.09857430966818]
  We introduce an extensive mathematics dataset called "MathQuest" sourced from the 11th and 12th standard Mathematics NCERT textbooks. We conduct fine-tuning experiments with three prominent large language models: LLaMA-2, WizardMath, and MAmmoTH. Our experiments reveal that among the three models, MAmmoTH-13B emerges as the most proficient, achieving the highest level of competence in solving the presented mathematical problems.
  arXiv  Detail & Related papers  (2024-04-19T08:45:42Z)
• Machine Learning Augmented Branch and Bound for Mixed Integer Linear Programming [11.293025183996832]
  Mixed Linear Programming (MILP) offers a powerful modeling language for a wide range of applications. In recent years, there has been an explosive development in the use of machine learning algorithms for enhancing all main tasks involved in the branch-and-bound algorithm. In particular, we give detailed attention to machine learning algorithms that automatically optimize some metric of branch-and-bound efficiency.
  arXiv  Detail & Related papers  (2024-02-08T09:19:26Z)
• MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning [52.97768001837269]
  We present a method to fine-tune open-source language models, enabling them to use code for modeling and deriving math equations. We propose a method of generating novel and high-quality datasets with math problems and their code-based solutions. This approach yields the MathCoder models, a family of models capable of generating code-based solutions for solving challenging math problems.
  arXiv  Detail & Related papers  (2023-10-05T17:52:09Z)
• The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks [59.26515696183751]
  We show that algorithm discovery in neural networks is sometimes more complex. We show that even simple learning problems can admit a surprising diversity of solutions.
  arXiv  Detail & Related papers  (2023-06-30T17:59:13Z)
• JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding [74.12405417718054]
  This paper aims to advance the mathematical intelligence of machines by presenting the first Chinese mathematical pre-trained language model(PLM) Unlike other standard NLP tasks, mathematical texts are difficult to understand, since they involve mathematical terminology, symbols and formulas in the problem statement. We design a novel curriculum pre-training approach for improving the learning of mathematical PLMs, consisting of both basic and advanced courses.
  arXiv  Detail & Related papers  (2022-06-13T17:03:52Z)
• Machine Learning Methods in Solving the Boolean Satisfiability Problem [72.21206588430645]
  The paper reviews the recent literature on solving the Boolean satisfiability problem (SAT) with machine learning techniques. We examine the evolving ML-SAT solvers from naive classifiers with handcrafted features to the emerging end-to-end SAT solvers such as NeuroSAT.
  arXiv  Detail & Related papers  (2022-03-02T05:14:12Z)
• Learning to Match Mathematical Statements with Proofs [37.38969121408295]
  The task is designed to improve the processing of research-level mathematical texts. We release a dataset for the task, consisting of over 180k statement-proof pairs. We show that considering the assignment problem globally and using weighted bipartite matching algorithms helps a lot in tackling the task.
  arXiv  Detail & Related papers  (2021-02-03T15:38:54Z)
• Strong Generalization and Efficiency in Neural Programs [69.18742158883869]
  We study the problem of learning efficient algorithms that strongly generalize in the framework of neural program induction. By carefully designing the input / output interfaces of the neural model and through imitation, we are able to learn models that produce correct results for arbitrary input sizes.
  arXiv  Detail & Related papers  (2020-07-07T17:03:02Z)

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.