Fast Generation for Convolutional Autoregressive Models
Prajit Ramachandran
T. Paine
Pooya Khorrami
Mohammad Babaeizadeh
Shiyu Chang
Yang Zhang
Mark Hasegawa-Johnson
R. Campbell
Thomas S. Huang

Abstract
Convolutional autoregressive models have recently demonstrated state-of-the-art performance on a number of generation tasks. While fast, parallel training methods have been crucial for their success, generation is typically implemented in a na\"{i}ve fashion where redundant computations are unnecessarily repeated. This results in slow generation, making such models infeasible for production environments. In this work, we describe a method to speed up generation in convolutional autoregressive models. The key idea is to cache hidden states to avoid redundant computation. We apply our fast generation method to the Wavenet and PixelCNN++ models and achieve up to and speedups respectively.
View on arXivComments on this paper