paper-with-me

Papers

Linear algebra with transformers

2021-12-03 · François Charton

Transformers can learn to perform numerical computations from examples only. I study nine problems of linear algebra, from basic matrix operations to eigenvalue decomposition and inversion, and introduce and discuss four encoding schemes to represent real numbers. On all problems, transformers trained on sets of random matrices achieve high accuracies (over 90%). The models are robust to noise, and can generalize out of their training distribution. In particular, models trained to predict Laplace-distributed eigenvalues generalize to different classes of matrices: Wigner matrices or matrices with positive eigenvalues. The reverse is not true.

📄 PDF Abstract BibTeX arXiv:2112.01898

Code (2)

facebookresearch/lawt 공식 구현 pytorch
ml4sci/symbahep pytorch

Tasks

Automated Theorem ProvingFew-Shot Learning

Similar Papers 제목 키워드 기반

Linear algebra with transformers

2021-09-29 · Francois Charton

Most applications of transformers to mathematics, from integration to theorem proving, focus on symbolic computation. In this paper, we show that transformers can be trained to perform numerical calculations with high ac…

Automated Theorem ProvingFew-Shot Learning

Algebraic Language Models for Inverse Design of Metamaterials via Diffusion Transformers

2025-07-21 · Li Zheng, Siddhant Kumar, Dennis M. Kochmann arxiv

Generative machine learning models have revolutionized material discovery by capturing complex structure-property relationships, yet extending these approaches to the inverse design of three-dimensional metamaterials rem…

Coinductive guide to inductive transformer heads

2023-02-03 · Adam Nemecek

We argue that all building blocks of transformer models can be expressed with a single concept: combinatorial Hopf algebra. Transformer learning emerges as a result of the subtle interplay between the algebraic and coalg…

Discovering Hidden Algebraic Structures via Transformers with Rank-Aware Beam GRPO

2025-08-21 · Jaeha Lee, Gio Huh, Ning Su, Tony Yue YU arxiv

Recent efforts have extended the capabilities of transformers in logical reasoning and symbolic computations. In this work, we investigate their capacity for non-linear latent pattern discovery in the context of function…

Synthetic Data GenerationReinforcement LearningLogical Reasoning

Fast computation of permutation equivariant layers with the partition algebra

2023-03-10 · Charles Godfrey, Michael G. Rawson, Davis Brown, Henry Kvinge

Linear neural network layers that are either equivariant or invariant to permutations of their inputs form core building blocks of modern deep learning architectures. Examples include the layers of DeepSets, as well as l…