GitHub

Sparse Matrices for Machine Learning in Python.md

Sparse matrices are data structures that efficiently store and operate on matrices with mostly zero elements. They are crucial in machine learning for handling large datasets with many zero values, ...
IEEE

Sparse Matrix

This chapter examines the seven variants of sparse matrices implemented in the Scipy library. These seven variants include: coordinate sparse matrix, compressed sparse column matrix, compressed sparse ...
GitHub

Fast Block Sparse Matrices for Pytorch

This PyTorch extension provides a drop-in replacement for torch.nn.Linear using block sparse matrices instead of dense ones. It enables very easy experimentation with sparse matrices since you can ...
IEEE

A Balanced Sparse Matrix Convolution Accelerator for Efficient CNN Training

Abstract: Sparse Convolutional Neural Network (CNN) training is well known to be time-consuming due to significant off-chip memory traffic. To effectively deploy sparse training, existing accelerators ...
acm.org

Solving Sparse Linear Systems Faster than Matrix Multiplication

Presenting an algorithm that solves linear systems with sparse coefficient matrices asymptotically faster than matrix multiplication for any ω > 2. Our algorithm can be viewed as an efficient, ...
Scientific Research Publishing

Positive-Definite Sparse Precision Matrix Estimation ()

1 School of Mathematics and Computer Science, Anhui Normal University, Wuhu, China. 2 School of Mathematics and Statistics, Huazhong University of Science and Technology, Wuhan, China. The ...