Sai Rajeshwar — accepted AI-conference papers

2018

Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data

Amjad Almahairi, Sai Rajeshwar, Alessandro Sordoni, Philip Bachman, Aaron Courville

ICML 2018oral

Learning inter-domain mappings from unpaired data can improve performance in structured prediction tasks, such as image segmentation, by reducing the need for paired data. CycleGAN was recently proposed for this problem, but critically assumes the underlying inter-domain mapping is approximately det…

Cited by 563 Source ↗PDF ↗Scholar ↗

2018

Mutual Information Neural Estimation

Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeshwar, Sherjil Ozair, Yoshua Bengio, Aaron Courville +1

ICML 2018oral

We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks. We present a Mutual Information Neural Estimator (MINE) that is linearly scalable in dimensionality as well as in sample size, trainable t…

Cited by 1758 Source ↗PDF ↗Scholar ↗