Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Ben Poole

Variational Diffusion Models


Jul 12, 2021
Diederik P. Kingma, Tim Salimans, Ben Poole, Jonathan Ho


  Access Paper or Ask Questions

Learning Energy-Based Models by Diffusion Recovery Likelihood


Dec 15, 2020
Ruiqi Gao, Yang Song, Ben Poole, Ying Nian Wu, Diederik P. Kingma


  Access Paper or Ask Questions

Score-Based Generative Modeling through Stochastic Differential Equations


Nov 26, 2020
Yang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole


  Access Paper or Ask Questions

VIB is Half Bayes


Nov 17, 2020
Alexander A Alemi, Warren R Morningstar, Ben Poole, Ian Fischer, Joshua V Dillon


  Access Paper or Ask Questions

Non-saturating GAN training as divergence minimization


Oct 15, 2020
Matt Shannon, Ben Poole, Soroosh Mariooryad, Tom Bagby, Eric Battenberg, David Kao, Daisy Stanton, RJ Skerry-Ryan


  Access Paper or Ask Questions

Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves


Sep 23, 2020
Luke Metz, Niru Maheswaranathan, C. Daniel Freeman, Ben Poole, Jascha Sohl-Dickstein


  Access Paper or Ask Questions

What makes for good views for contrastive learning


May 20, 2020
Yonglong Tian, Chen Sun, Ben Poole, Dilip Krishnan, Cordelia Schmid, Phillip Isola

* submitted to ECCV 2020 

  Access Paper or Ask Questions

Using a thousand optimization tasks to learn hyperparameter search strategies


Mar 11, 2020
Luke Metz, Niru Maheswaranathan, Ruoxi Sun, C. Daniel Freeman, Ben Poole, Jascha Sohl-Dickstein


  Access Paper or Ask Questions

Regularized Autoencoders via Relaxed Injective Probability Flow


Feb 20, 2020
Abhishek Kumar, Ben Poole, Kevin Murphy

* AISTATS 2020 

  Access Paper or Ask Questions

On Implicit Regularization in $β$-VAEs


Feb 09, 2020
Abhishek Kumar, Ben Poole


  Access Paper or Ask Questions

Weakly-Supervised Disentanglement Without Compromises


Feb 07, 2020
Francesco Locatello, Ben Poole, Gunnar Rätsch, Bernhard Schölkopf, Olivier Bachem, Michael Tschannen


  Access Paper or Ask Questions

Weakly Supervised Disentanglement with Guarantees


Oct 22, 2019
Rui Shu, Yining Chen, Abhishek Kumar, Stefano Ermon, Ben Poole


  Access Paper or Ask Questions

On Predictive Information Sub-optimality of RNNs


Oct 21, 2019
Zhe Dong, Deniz Oktay, Ben Poole, Alexander A. Alemi


  Access Paper or Ask Questions

Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation


Jun 06, 2019
Raphael Gontijo Lopes, Dong Yin, Ben Poole, Justin Gilmer, Ekin D. Cubuk


  Access Paper or Ask Questions

Discrete Flows: Invertible Generative Models of Discrete Data


May 24, 2019
Dustin Tran, Keyon Vafa, Kumar Krishna Agrawal, Laurent Dinh, Ben Poole


  Access Paper or Ask Questions

On Variational Bounds of Mutual Information


May 16, 2019
Ben Poole, Sherjil Ozair, Aaron van den Oord, Alexander A. Alemi, George Tucker

* ICML 2019 

  Access Paper or Ask Questions

Preventing Posterior Collapse with delta-VAEs


Jan 10, 2019
Ali Razavi, Aäron van den Oord, Ben Poole, Oriol Vinyals


  Access Paper or Ask Questions

Fixing a Broken ELBO


Feb 13, 2018
Alexander A. Alemi, Ben Poole, Ian Fischer, Joshua V. Dillon, Rif A. Saurous, Kevin Murphy

* 21 pages, 9 figures 

  Access Paper or Ask Questions

Categorical Reparameterization with Gumbel-Softmax


Aug 05, 2017
Eric Jang, Shixiang Gu, Ben Poole


  Access Paper or Ask Questions

On the Expressive Power of Deep Neural Networks


Jun 18, 2017
Maithra Raghu, Ben Poole, Jon Kleinberg, Surya Ganguli, Jascha Sohl-Dickstein

* Accepted to ICML 2017 

  Access Paper or Ask Questions

Continual Learning Through Synaptic Intelligence


Jun 12, 2017
Friedemann Zenke, Ben Poole, Surya Ganguli

* ICML 2017 

  Access Paper or Ask Questions

Unrolled Generative Adversarial Networks


May 12, 2017
Luke Metz, Ben Poole, David Pfau, Jascha Sohl-Dickstein


  Access Paper or Ask Questions

Adversarially Learned Inference


Feb 21, 2017
Vincent Dumoulin, Ishmael Belghazi, Ben Poole, Olivier Mastropietro, Alex Lamb, Martin Arjovsky, Aaron Courville


  Access Paper or Ask Questions

Improved generator objectives for GANs


Dec 08, 2016
Ben Poole, Alexander A. Alemi, Jascha Sohl-Dickstein, Anelia Angelova

* NIPS 2016 Workshop on Adversarial Training 

  Access Paper or Ask Questions

Survey of Expressivity in Deep Neural Networks


Nov 24, 2016
Maithra Raghu, Ben Poole, Jon Kleinberg, Surya Ganguli, Jascha Sohl-Dickstein

* Presented at NIPS 2016 Workshop on Interpretable Machine Learning in Complex Systems 

  Access Paper or Ask Questions

The Fast Bilateral Solver


Jul 22, 2016
Jonathan T. Barron, Ben Poole


  Access Paper or Ask Questions

Exponential expressivity in deep neural networks through transient chaos


Jun 17, 2016
Ben Poole, Subhaneil Lahiri, Maithra Raghu, Jascha Sohl-Dickstein, Surya Ganguli

* Fixed equation references 

  Access Paper or Ask Questions