English
Related papers

Related papers: Multiplication-Free Transformer Training via Piece…

200 papers

Ensemble learning is a widespread technique to improve the prediction performance of neural networks. However, it comes at the price of increased memory and inference time. In this work we propose a novel model fusion technique called…

Machine Learning · Computer Science 2025-02-12 Muhammed Öz , Nicholas Kiefer , Charlotte Debus , Jasmin Hörter , Achim Streit , Markus Götz

The use of low-precision fixed-point arithmetic along with stochastic rounding has been proposed as a promising alternative to the commonly used 32-bit floating point arithmetic to enhance training neural networks training in terms of…

Machine Learning · Computer Science 2018-04-17 Marc Ortiz , Adrián Cristal , Eduard Ayguadé , Marc Casas

To reduce memory footprint and run-time latency, techniques such as neural network pruning and binarization have been explored separately. However, it is unclear how to combine the best of the two worlds to get extremely small and efficient…

Computer Vision and Pattern Recognition · Computer Science 2018-12-12 Yinghao Xu , Xin Dong , Yudian Li , Hao Su

In this paper, we propose the use of in-training matrix factorization to reduce the model size for neural machine translation. Using in-training matrix factorization, parameter matrices may be decomposed into the products of smaller…

Computation and Language · Computer Science 2020-03-25 Zachary Kaden , Teven Le Scao , Raphael Olivier

In this paper, we present an approach for minimizing the computational complexity of trained Convolutional Neural Networks (ConvNet). The idea is to approximate all elements of a given ConvNet and replace the original convolutional filters…

Machine Learning · Computer Science 2022-08-02 R. J. Cintra , S. Duffner , C. Garcia , A. Leite

The successful training of deep neural networks requires addressing challenges such as overfitting, numerical instabilities leading to divergence, and increasing variance in the residual stream. A common solution is to apply regularization…

Machine Learning · Computer Science 2025-11-20 Jörg K. H. Franke , Urs Spiegelhalter , Marianna Nezhurina , Jenia Jitsev , Frank Hutter , Michael Hefenbrock

Fast linear transforms are ubiquitous in machine learning, including the discrete Fourier transform, discrete cosine transform, and other structured transformations such as convolutions. All of these transforms can be represented by dense…

Machine Learning · Computer Science 2021-01-01 Tri Dao , Albert Gu , Matthew Eichhorn , Atri Rudra , Christopher Ré

Machine learning frameworks adopt iterative optimizers to train neural networks. Conventional eager execution separates the updating of trainable parameters from forward and backward computations. However, this approach introduces…

Machine Learning · Computer Science 2021-04-02 Zixuan Jiang , Jiaqi Gu , Mingjie Liu , Keren Zhu , David Z. Pan

Neural networks are commonly used as models for classification for a wide variety of tasks. Typically, a learned affine transformation is placed at the end of such models, yielding a per-class value used for classification. This classifier…

Machine Learning · Computer Science 2018-03-21 Elad Hoffer , Itay Hubara , Daniel Soudry

In this work, we propose to quantize all parts of standard classification networks and replace the activation-weight--multiply step with a simple table-based lookup. This approach results in networks that are free of floating-point…

Machine Learning · Computer Science 2019-06-13 Michele Covell , David Marwood , Shumeet Baluja , Nick Johnston

Ootomo, Ozaki, and Yokota [Int. J. High Perform. Comput. Appl., 38 (2024), p. 297-313] have proposed a strategy to recast a floating-point matrix multiplication in terms of integer matrix products. The factors A and B are split into integer…

Numerical Analysis · Mathematics 2026-05-11 Ahmad Abdelfattah , Jack Dongarra , Massimiliano Fasi , Mantas Mikaitis , Françoise Tisseur

We show that artificial neural networks with rectifier units as activation functions can exactly represent the piecewise affine function that results from the formulation of model predictive control of linear time-invariant systems. The…

Optimization and Control · Mathematics 2021-01-01 Benjamin Karg , Sergio Lucia

It is known that the multiplication of an $N \times M$ matrix with an $M \times P$ matrix can be performed using fewer multiplications than what the naive $NMP$ approach suggests. The most famous instance of this is Strassen's algorithm for…

Artificial Intelligence · Computer Science 2023-07-18 Arnaud Deza , Chang Liu , Pashootan Vaezipoor , Elias B. Khalil

This paper describes a method for accelerating large scale Artificial Neural Networks (ANN) training using multi-GPUs by reducing the forward and backward passes to matrix multiplication. We propose an out-of-core multi-GPU matrix…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-11-16 Linnan Wang , Wei Wu , Jianxiong Xiao , Yang Yi

Continual learning is a desirable feature in many modern machine learning applications, which allows in-field adaptation and updating, ranging from accommodating distribution shift, to fine-tuning, and to learning new tasks. For…

Machine Learning · Computer Science 2023-10-06 Martin Schiemer , Clemens JS Schaefer , Jayden Parker Vap , Mark James Horeni , Yu Emma Wang , Juan Ye , Siddharth Joshi

Previous work has shown that it is possible to train deep neural networks with low precision weights and activations. In the extreme case it is even possible to constrain the network to binary values. The costly floating point…

Neural and Evolutionary Computing · Computer Science 2017-11-30 Sam Leroux , Steven Bohez , Tim Verbelen , Bert Vankeirsbilck , Pieter Simoens , Bart Dhoedt

A large fraction of the arithmetic operations required to evaluate deep neural networks (DNNs) consists of matrix multiplications, in both convolution and fully connected layers. We perform end-to-end learning of low-cost approximations of…

Machine Learning · Computer Science 2018-06-11 Michael Tschannen , Aran Khanna , Anima Anandkumar

Machine learning methods have nowadays become easy-to-use tools for constructing high-dimensional interatomic potentials with ab initio accuracy. Although machine learned interatomic potentials are generally orders of magnitude faster than…

Computational Physics · Physics 2021-02-24 Yaolong Zhang , Ce Hu , Bin Jiang

We introduce ReplaceMe, a generalized training-free depth pruning method that effectively replaces transformer blocks with a linear operation, while maintaining high performance for low compression ratios. In contrast to conventional…

Computation and Language · Computer Science 2026-02-20 Dmitriy Shopkhoev , Ammar Ali , Magauiya Zhussip , Valentin Malykh , Stamatios Lefkimmiatis , Nikos Komodakis , Sergey Zagoruyko

In recent years, artificial neural networks have developed into a powerful tool for addressing a multitude of problems for which classical solution approaches reach their limits. However, it is still unclear why gradient descent…

Machine Learning · Computer Science 2026-05-20 Arnulf Jentzen , Timo Kröger