Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations

Abstract

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 $O(N\log N)$ 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.

International Conference on Machine Learning (ICML) 2019

Cited by in corpus (11)

• HiPPO: Recurrent Memory with Optimal Polynomial Projections
• Low-Memory Neural Network Training: A Technical Report
• Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms
• Scatterbrain: Unifying Sparse and Low-rank Attention Approximation
• Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps
• Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models
• Sparse Linear Networks with a Fixed Butterfly Structure: Theory and Practice
• Spurious Valleys, NP-hardness, and Tractability of Sparse Matrix Factorization With Fixed Support
• Rethinking Neural Operations for Diverse Tasks
• Quantized Neural Network Inference with Precision Batching
• Building Compact and Robust Deep Neural Networks with Toeplitz Matrices