English
Related papers

Related papers: Linear algebra with transformers

200 papers

Whether neural networks can serve as cognitive models of morphological learning remains an open question. Recent work has shown that encoder-decoder models can acquire irregular patterns, but evidence that they generalize these patterns…

Computation and Language · Computer Science 2026-02-17 Akhilesh Kakolu Ramarao , Kevin Tang , Dinah Baer-Henney

Grokking in transformers trained on algorithmic tasks is characterized by a long delay between training-set fit and abrupt generalization, but the source of that delay remains poorly understood. In encoder-decoder arithmetic models, we…

Machine Learning · Computer Science 2026-04-16 Laura Gomezjurado Gonzalez

Despite their simplicity, linear models perform well at time series forecasting, even when pitted against deeper and more expensive models. A number of variations to the linear model have been proposed, often including some form of feature…

Machine Learning · Computer Science 2024-03-26 William Toner , Luke Darlow

Linear programming has played a crucial role in shaping decision-making, resource allocation, and cost reduction in various domains. In this paper, we investigate the application of overparametrized neural networks and their implicit bias…

Optimization and Control · Mathematics 2023-10-05 Haoyue Wang , Promit Ghosal , Rahul Mazumder

Which transformer scaling regimes are able to perfectly solve different classes of algorithmic problems? While tremendous empirical advances have been attained by transformer-based neural networks, a theoretical understanding of their…

Based on the property that solving the system of linear matrix equations via the column space and the row space projections boils down to an approximation in the least squares error sense, a formulation for learning the weight matrices of…

Machine Learning · Computer Science 2018-11-21 Kar-Ann Toh

Five equivalence classes had been found for systems of two second-order ordinary differential equations, transformable to linear equations (linearizable systems) by a change of variables. An "optimal (or simplest) canonical form" of linear…

Classical Analysis and ODEs · Mathematics 2011-04-19 Muhammad Safdar , Asghar Qadir , Sajid Ali

We present a deep transformation model for probabilistic regression. Deep learning is known for outstandingly accurate predictions on complex data but in regression tasks, it is predominantly used to just predict a single number. This…

Machine Learning · Statistics 2020-04-02 Beate Sick , Torsten Hothorn , Oliver Dürr

In this chapter we provide a theoretically founded investigation of state-of-the-art learning approaches for inverse problems from the point of view of spectral reconstruction operators. We give an extended definition of regularization…

Numerical Analysis · Mathematics 2024-06-05 Martin Burger , Samira Kabri

We assume that every element of a matrix has a small, individual error, and model it by an external number, which is the sum of a nonstandard real number and a neutrix, the latter being a convex (external) set having the group property. The…

Rings and Algebras · Mathematics 2019-07-31 Nam van Tran , Imme van den Berg

Transformer networks have seen great success in natural language processing and machine vision, where task objectives such as next word prediction and image classification benefit from nuanced context sensitivity across high-dimensional…

Machine Learning · Computer Science 2022-12-13 Yuxuan Li , James L. McClelland

Neural sequence models, especially transformers, exhibit a remarkable capacity for in-context learning. They can construct new predictors from sequences of labeled examples $(x, f(x))$ presented in the input without further parameter…

Machine Learning · Computer Science 2023-05-19 Ekin Akyürek , Dale Schuurmans , Jacob Andreas , Tengyu Ma , Denny Zhou

This paper studies the learning of linear operators between infinite-dimensional Hilbert spaces. The training data comprises pairs of random input vectors in a Hilbert space and their noisy images under an unknown self-adjoint linear…

Statistics Theory · Mathematics 2023-05-12 Maarten V. de Hoop , Nikola B. Kovachki , Nicholas H. Nelsen , Andrew M. Stuart

Deep convolutional networks (convnets) show a remarkable ability to learn disentangled representations. In recent years, the generalization of deep learning to Lie groups beyond rigid motion in $\mathbb{R}^n$ has allowed to build convnets…

Machine Learning · Computer Science 2020-11-13 Christopher Ick , Vincent Lostanlen

Linear algebra is usually defined over a field such as the reals or complex numbers. It is possible to extend this to skew fields such as the quaternions. However, to the authors' knowledge there is no commonly accepted notation of linear…

Rings and Algebras · Mathematics 2014-03-21 Dominik Schulz , Reiner S. Thomä

Machine learning (ML) formalizes the problem of getting computers to learn from experience as optimization of performance according to some metric(s) on a set of data examples. This is in contrast to requiring behaviour specified in advance…

Machine Learning · Computer Science 2022-10-19 Tegan Maharaj

Classical and exceptional Lie algebras and their representations are among the most important tools in the analysis of symmetry in physical systems. In this letter we show how the computation of tensor products and branching rules of…

High Energy Physics - Theory · Physics 2021-04-22 Heng-Yu Chen , Yang-Hui He , Shailesh Lal , Suvajit Majumder

Many successful deep learning architectures are equivariant to certain transformations in order to conserve parameters and improve generalization: most famously, convolution layers are equivariant to shifts of the input. This approach only…

Machine Learning · Computer Science 2021-03-31 Allan Zhou , Tom Knowles , Chelsea Finn

The Transformer architecture has become a dominant choice in many domains, such as natural language processing and computer vision. Yet, it has not achieved competitive performance on popular leaderboards of graph-level prediction compared…

Machine Learning · Computer Science 2021-11-25 Chengxuan Ying , Tianle Cai , Shengjie Luo , Shuxin Zheng , Guolin Ke , Di He , Yanming Shen , Tie-Yan Liu

Large language models exhibit surprising emergent generalization properties, yet also struggle on many simple reasoning tasks such as arithmetic and parity. This raises the question of if and when Transformer models can learn the true…

Machine Learning · Computer Science 2023-10-25 Hattie Zhou , Arwen Bradley , Etai Littwin , Noam Razin , Omid Saremi , Josh Susskind , Samy Bengio , Preetum Nakkiran
‹ Prev 1 3 4 5 6 7 10 Next ›