Search Results for author:
Found 3 papers, 3 papers with code
Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps
Modern neural network architectures use structured linear transformations, such as low-rank matrices, sparse matrices, permutations, and the Fourier transform, to improve inference speed and reduce memory usage compared to general linear maps.
Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations
Fast linear transforms are ubiquitous in machine learning, including the discrete Fourier transform, discrete cosine transform, and other structured transformations such as convolutions.
Fast Counting in Machine Learning Applications
We propose scalable methods to execute counting queries in machine learning applications.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
