English
Related papers

Related papers: What if Neural Networks had SVDs?

200 papers

Convolution is the core operation for many deep neural networks. The Winograd convolution algorithms have been shown to accelerate the widely-used small convolution sizes. Quantized neural networks can effectively reduce model sizes and…

Neural and Evolutionary Computing · Computer Science 2019-01-09 Lingchuan Meng , John Brothers

The prevalence of convolution in applications within signal processing, deep neural networks, and numerical solvers has motivated the development of numerous fast convolution algorithms. In many of these problems, convolution is performed…

Numerical Analysis · Mathematics 2020-07-03 Caleb Ju , Edgar Solomonik

This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs). Unlike existing methods that are designed for approximating linear filters or linear responses, our method takes the nonlinear units into…

Computer Vision and Pattern Recognition · Computer Science 2014-11-18 Xiangyu Zhang , Jianhua Zou , Xiang Ming , Kaiming He , Jian Sun

Recent advances in Voice Activity Detection (VAD) are driven by artificial and Recurrent Neural Networks (RNNs), however, using a VAD system in battery-operated devices requires further power efficiency. This can be achieved by neuromorphic…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-01 Flavio Martinelli , Giorgia Dellaferrera , Pablo Mainar , Milos Cernak

We introduce an algorithm for efficiently representing convolution with zero-padding and stride as a sparse transformation matrix, applied to a vectorized input through sparse matrix-vector multiplication (SpMV). We provide a theoretical…

Machine Learning · Computer Science 2024-12-02 Zan Chaudhry

The oriented singular value decomposition (O-SVD) proposed by Zeng and Ng provides a hybrid approach to the t-product based third-order tensor singular value decomposition with the transform matrix being a factor matrix of the higher order…

Numerical Analysis · Mathematics 2023-02-28 Minghui Ding , Yimin Wei , Pengpeng Xie

Transformer language models generate text autoregressively, making inference latency proportional to the number of tokens generated. Speculative decoding reduces this latency without sacrificing output quality, by leveraging a small draft…

Machine Learning · Computer Science 2025-10-24 Clara Mohri , Haim Kaplan , Tal Schuster , Yishay Mansour , Amir Globerson

An enhanced Kogbetliantz method for the singular value decomposition (SVD) of general matrices of order two is proposed. The method consists of three phases: an almost exact prescaling, that can be beneficial to the LAPACK's xLASV2 routine…

Numerical Analysis · Mathematics 2026-02-10 Vedran Novaković

Recurrent neural networks (RNNs) have been used extensively and with increasing success to model various types of sequential data. Much of this progress has been achieved through devising recurrent units and architectures with the…

Machine Learning · Statistics 2017-03-06 Yacine Jernite , Edouard Grave , Armand Joulin , Tomas Mikolov

In this paper a two-sided, parallel Kogbetliantz-type algorithm for the hyperbolic singular value decomposition (HSVD) of real and complex square matrices is developed, with a single assumption that the input matrix, of order $n$, admits…

Numerical Analysis · Mathematics 2022-05-10 Vedran Novaković , Sanja Singer

The goal of this paper is to test three classes of neural network (NN) architectures based on four-dimensional (4D) hypercomplex algebras for time series prediction. We evaluate different architectures, varying the input layers to include…

Neural and Evolutionary Computing · Computer Science 2024-02-14 Radosław Kycia , Agnieszka Niemczynowicz

Stochastic Gradient Descent (SGD) is a workhorse in machine learning, yet its slow convergence can be a computational bottleneck. Variance reduction techniques such as SAG, SVRG and SAGA have been proposed to overcome this weakness,…

Machine Learning · Computer Science 2016-02-29 Thomas Hofmann , Aurelien Lucchi , Simon Lacoste-Julien , Brian McWilliams

We describe novel subgradient methods for a broad class of matrix optimization problems involving nuclear norm regularization. Unlike existing approaches, our method executes very cheap iterations by combining low-rank stochastic…

Machine Learning · Computer Science 2012-07-03 Haim Avron , Satyen Kale , Shiva Kasiviswanathan , Vikas Sindhwani

Modern neural network-based algorithms are able to produce highly accurate depth estimates from stereo image pairs, nearly matching the reliability of measurements from more expensive depth sensors. However, this accuracy comes with a…

Computer Vision and Pattern Recognition · Computer Science 2019-03-13 Kyle Yee , Ayan Chakrabarti

Convergence of a matrix decomposition technique, the multi-field singular value decomposition (MFSVD) which efficiently analyzes nonlinear correlations by simultaneously decomposing multiple fields, is investigated. Toward applications in…

Fluid Dynamics · Physics 2024-11-08 Go Yatomi , Motoki Nakata

Discovering constants of motion is meaningful in helping understand the dynamical systems, but inevitably needs proficient mathematical skills and keen analytical capabilities. With the prevalence of deep learning, methods employing neural…

Machine Learning · Computer Science 2025-04-15 Wenqi Fang , Chao Chen , Yongkui Yang , Zheng Wang

Spiking Neural Networks (SNNs) operate with asynchronous discrete events (or spikes) which can potentially lead to higher energy-efficiency in neuromorphic hardware implementations. Many works have shown that an SNN for inference can be…

Machine Learning · Computer Science 2020-05-06 Nitin Rathi , Gopalakrishnan Srinivasan , Priyadarshini Panda , Kaushik Roy

Numerical simulation of ordinary differential equations (ODEs) can be challenging when the system exhibits high accelerations and rapidly changing dynamics. Under these conditions the ODE solver often needs to take very small time steps in…

Numerical Analysis · Mathematics 2026-05-11 Andrew Tagg , Andrew Frandsen , Andrew Ning

We study the general approach to accelerating the convergence of the most widely used solution method of Markov decision processes with the total expected discounted reward. Inspired by the monotone behavior of the contraction mappings in…

Optimization and Control · Mathematics 2008-03-28 Oleksandr Shlakhter , Chi-Guhn Lee , Dmitry Khmelev , Nasser Jaber

We present a generalisation of the pseudoinverse operation to pairs of matrices, as opposed to single matrices alone. We note the fact that the Singular Value Decomposition can be used to compute the ordinary Moore-Penrose pseudoinverse. We…

Rings and Algebras · Mathematics 2021-12-07 Ran Gutin