Linear algebra with transformers

• URL: http://arxiv.org/abs/2112.01898v1
• Date: Fri, 3 Dec 2021 13:21:57 GMT
• Title: Linear algebra with transformers
• Authors: Fran\c{c}ois Charton
• Abstract summary: We show that transformers can be trained to perform numerical calculations with high accuracy. We consider problems of linear algebra: matrix transposition, addition, multiplication, eigenvalues and vectors, singular value decomposition, and inversion.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 accuracy. We consider problems of linear algebra: matrix transposition, addition, multiplication, eigenvalues and vectors, singular value decomposition, and inversion. Training small transformers (up to six layers) over datasets of random matrices, we achieve high accuracies (over 90%) on all problems. We also show that trained models can generalize out of their training distribution, and that out-of-domain accuracy can be greatly improved by working from more diverse datasets (in particular, by training from matrices with non-independent and identically distributed coefficients). Finally, we show that few-shot learning can be leveraged to re-train models to solve larger problems.

Related papers

• MemoryFormer: Minimize Transformer Computation by Removing Fully-Connected Layers [43.39466934693055]
  We present MemoryFormer, a novel transformer architecture which significantly reduces the computational complexity (FLOPs) from a new perspective. This is made possible by utilizing an alternative method for feature transformation to replace the linear projection of fully-connected layers. We conduct extensive experiments on various benchmarks to demonstrate the effectiveness of the proposed model.
  arXiv  Detail & Related papers  (2024-11-20T02:41:53Z)
• Graph Transformers Dream of Electric Flow [72.06286909236827]
  We show that the linear Transformer, when applied to graph data, can implement algorithms that solve canonical problems. We present explicit weight configurations for implementing each such graph algorithm, and we bound the errors of the constructed Transformers by the errors of the underlying algorithms.
  arXiv  Detail & Related papers  (2024-10-22T05:11:45Z)
• Learning Linear Attention in Polynomial Time [115.68795790532289]
  We provide the first results on learnability of single-layer Transformers with linear attention. We show that linear attention may be viewed as a linear predictor in a suitably defined RKHS. We show how to efficiently identify training datasets for which every empirical riskr is equivalent to the linear Transformer.
  arXiv  Detail & Related papers  (2024-10-14T02:41:01Z)
• Dissecting Multiplication in Transformers: Insights into LLMs [23.109124772063574]
  We focus on a typical arithmetic task, integer multiplication, to explore and explain the imperfection of transformers in this domain. We provide comprehensive analysis of a vanilla transformer trained to perform n-digit integer multiplication. We propose improvements to enhance transformers performance on multiplication tasks.
  arXiv  Detail & Related papers  (2024-07-22T04:07:26Z)
• Optimal Matrix-Mimetic Tensor Algebras via Variable Projection [0.0]
  Matrix mimeticity arises from interpreting tensors as operators that can be multiplied, factorized, and analyzed analogous to matrices. We learn optimal linear mappings and corresponding tensor representations without relying on prior knowledge of the data. We provide original theory of uniqueness of the transformation and convergence analysis of our variable-projection-based algorithm.
  arXiv  Detail & Related papers  (2024-06-11T04:52:23Z)
• CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra [62.37017125812101]
  We propose a simple but general framework for large-scale linear algebra problems in machine learning, named CoLA. By combining a linear operator abstraction with compositional dispatch rules, CoLA automatically constructs memory and runtime efficient numerical algorithms. We showcase its efficacy across a broad range of applications, including partial differential equations, Gaussian processes, equivariant model construction, and unsupervised learning.
  arXiv  Detail & Related papers  (2023-09-06T14:59:38Z)
• Large-scale gradient-based training of Mixtures of Factor Analyzers [67.21722742907981]
  This article contributes both a theoretical analysis as well as a new method for efficient high-dimensional training by gradient descent. We prove that MFA training and inference/sampling can be performed based on precision matrices, which does not require matrix inversions after training is completed. Besides the theoretical analysis and matrices, we apply MFA to typical image datasets such as SVHN and MNIST, and demonstrate the ability to perform sample generation and outlier detection.
  arXiv  Detail & Related papers  (2023-08-26T06:12:33Z)
• Transformers learn in-context by gradient descent [58.24152335931036]
  Training Transformers on auto-regressive objectives is closely related to gradient-based meta-learning formulations. We show how trained Transformers become mesa-optimizers i.e. learn models by gradient descent in their forward pass.
  arXiv  Detail & Related papers  (2022-12-15T09:21:21Z)
• What is my math transformer doing? -- Three results on interpretability and generalization [0.0]
  I show that incorrect model predictions still retain deep mathematical properties of the solution. I also show that the careful choice of a training dataset can accelerate training, while allowing the model to generalize out of its training distribution.
  arXiv  Detail & Related papers  (2022-10-31T22:31:13Z)
• Sketching Transformed Matrices with Applications to Natural Language Processing [76.6222695417524]
  We propose a space-efficient sketching algorithm for computing the product of a given small matrix with the transformed matrix. We show that our approach obtains small error and is efficient in both space and time.
  arXiv  Detail & Related papers  (2020-02-23T03:07:31Z)

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.