butterfly
Butterfly matrix multiplication in PyTorch
view repo
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 matrix-vector multiplication, yet each has a specialized and highly efficient (subquadratic) algorithm. We ask to what extent hand-crafting these algorithms and implementations is necessary, what structural priors they encode, and how much knowledge is required to automatically learn a fast algorithm for a provided structured transform. Motivated by a characterization of fast matrix-vector multiplication as products of sparse matrices, we introduce a parameterization of divide-and-conquer methods that is capable of representing a large class of transforms. This generic formulation can automatically learn an efficient algorithm for many important transforms; for example, it recovers the O(N N) Cooley-Tukey FFT algorithm to machine precision, for dimensions N up to 1024. Furthermore, our method can be incorporated as a lightweight replacement of generic matrices in machine learning pipelines to learn efficient and compressible transformations. On a standard task of compressing a single hidden-layer network, our method exceeds the classification accuracy of unconstrained matrices on CIFAR-10 by 3.9 points---the first time a structured approach has done so---with 4X faster inference speed and 40X fewer parameters.
READ FULL TEXT
Modern neural network architectures use structured linear transformation...
read it
In calculating integral or discrete transforms, fast algorithms for
mult...
read it
In this paper, we propose several dictionary learning algorithms for spa...
read it
Self size-estimating feedforward network (SSFN) is a feedforward multila...
read it
Fast Fourier transform, Wavelets, and other well-known transforms in sig...
read it
The ability to decompose a signal in an orthonormal basis (a set of
orth...
read it
We consider the task of building compact deep learning pipelines suitabl...
read it
Butterfly matrix multiplication in PyTorch
Comments
There are no comments yet.