Fetching the paper…

Reading the bibliography…

2017

Fast Generation for Convolutional Autoregressive Models

Ramachandran, Prajit, Paine, Tom Le, Khorrami, Pooya et al.

Original
PDF
Post on X

Understand

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.

Fast Generation for Convolutional Autoregressive Models · Around

Built on

Action-conditional video prediction using deep networks in atari games
Junhyuk Oh, Xiaoxiao Guo, Honglak Lee, Richard L Lewis, and Satinder Singh · 2015
Earlier work this paper cites.
Tensorflow: A system for large-scale machine learning
Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al · 2016
Earlier work this paper cites.

Similar

A guide to convolution arithmetic for deep learning
Original
Vincent Dumoulin and Francesco Visin · 2016
Cited alongside, same era.
Pixel recursive super resolution
Original
Ryan Dahl, Mohammad Norouzi, and Jonathon Shlens · 2017
Cited alongside, same era.
Neural machine translation in linear time
Original
Nal Kalchbrenner, Lasse Espeholt, Karen Simonyan, Aaron van den Oord, Alex Graves, and Koray Kavukcuoglu
Cited in the paper.
Video pixel networks
Original
Nal Kalchbrenner, Aaron van den Oord, Karen Simonyan, Ivo Danihelka, Oriol Vinyals, Alex Graves, and Koray Kavukcuoglu
Cited in the paper.
Wavenet: A generative model for raw audio
Original
Aaron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew Senior, and Koray Kavukcuoglu
Cited in the paper.
Pixel recurrent neural networks
Original
Aaron van den Oord, Nal Kalchbrenner, and Koray Kavukcuoglu
Cited in the paper.
Conditional image generation with pixelcnn decoders
Original
Aaron van den Oord, Nal Kalchbrenner, Oriol Vinyals, Lasse Espeholt, Alex Graves, and Koray Kavukcuoglu
Cited in the paper.

Then

Pixelcnn++: Improving the pixelcnn with discretized logistic mixture likelihood and other modifications
Original
Tim Salimans, Andrej Karpathy, Xi Chen, and Diederik P Kingma · 2017
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…