CWY Parametrization: a Solution for Parallelized Optimization of Orthogonal and Stiefel Matrices

Abstract

We introduce an efficient approach for optimization over orthogonal groups on highly parallel computation units such as GPUs or TPUs. As in earlier work, we parametrize an orthogonal matrix as a product of Householder reflections. However, to overcome low parallelization capabilities of computing Householder reflections sequentially, we propose employing an accumulation scheme called the compact WY (or CWY) transform -- a compact parallelization-friendly matrix representation for the series of Householder reflections. We further develop a novel Truncated CWY (or T-CWY) approach for Stiefel manifold parametrization which has a competitive complexity and, again, yields benefits when computed on GPUs and TPUs. We prove that our CWY and T-CWY methods lead to convergence to a stationary point of the training objective when coupled with stochastic gradient descent. We apply our methods to train recurrent neural network architectures in the tasks of neural machine translation and video prediction.

arXiv commentProceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021, San Diego, California, USA. PMLR: Volume 130. Copyright 2021 by the author(s)

References in corpus (8)

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Self-Supervised Visual Planning with Temporal Skip Connections
• Full-Capacity Unitary Recurrent Neural Networks
• Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks
• Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs
• Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform
• DizzyRNN: Reparameterizing Recurrent Neural Networks for Norm-Preserving Backpropagation