3.3k citations · 9.7k across the 40 of their papers we have counts for
6 papers · 1 filter
Weakly Supervised Disentanglement with Guarantees
Rui Shu, Yining Chen, Abhishek Kumar +2
Learning disentangled representations that correspond to factors of variation in real-world data is critical to interpretable and human-controllable machine learning. Recently, con…
On Predictive Information in RNNs
Zhe Dong, Deniz Oktay, Ben Poole +1
Certain biological neurons demonstrate a remarkable capability to optimally compress the history of sensory inputs while being maximally informative about the future. In this work,…
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation
Raphael Gontijo Lopes, Dong Yin, Ben Poole +2
Deploying machine learning systems in the real world requires both high accuracy on clean data and robustness to naturally occurring corruptions. While architectural advances have…
Discrete Flows: Invertible Generative Models of Discrete Data
Dustin Tran, Keyon Vafa, Kumar Krishna Agrawal +2
While normalizing flows have led to significant advances in modeling high-dimensional continuous distributions, their applicability to discrete distributions remains unknown. In th…
On Variational Bounds of Mutual Information
Ben Poole, Sherjil Ozair, Aaron van den Oord +2
Estimating and optimizing Mutual Information (MI) is core to many problems in machine learning; however, bounding MI in high dimensions is challenging. To establish tractable and s…
Preventing Posterior Collapse with delta-VAEs
Ali Razavi, Aäron van den Oord, Ben Poole +1
Due to the phenomenon of "posterior collapse," current latent variable generative models pose a challenging design choice that either weakens the capacity of the decoder or require…