Ben Poole

Non-saturating GAN training as divergence minimization

Non-saturating generative adversarial network (GAN) training is widely u...
10/15/2020 ∙ by Matt Shannon, et al. ∙ 0 ∙ share

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

Much as replacing hand-designed features with learned functions has revo...
09/23/2020 ∙ by Luke Metz, et al. ∙ 12 ∙ share

read it
What makes for good views for contrastive learning

Contrastive learning between multiple views of the data has recently ach...
05/20/2020 ∙ by Yonglong Tian, et al. ∙ 16 ∙ share

read it
Using a thousand optimization tasks to learn hyperparameter search strategies

We present TaskSet, a dataset of tasks for use in training and evaluatin...
02/27/2020 ∙ by Luke Metz, et al. ∙ 71 ∙ share

read it
Regularized Autoencoders via Relaxed Injective Probability Flow

Invertible flow-based generative models are an effective method for lear...
02/20/2020 ∙ by Abhishek Kumar, et al. ∙ 5 ∙ share

read it
Weakly-Supervised Disentanglement Without Compromises

Intelligent agents should be able to learn useful representations by obs...
02/07/2020 ∙ by Francesco Locatello, et al. ∙ 20 ∙ share

read it
On Implicit Regularization in β-VAEs

While the impact of variational inference (VI) on posterior inference in...
01/31/2020 ∙ by Abhishek Kumar, et al. ∙ 9 ∙ share

read it
Weakly Supervised Disentanglement with Guarantees

Learning disentangled representations that correspond to factors of vari...
10/22/2019 ∙ by Rui Shu, et al. ∙ 12 ∙ share

read it
On Predictive Information Sub-optimality of RNNs

Certain biological neurons demonstrate a remarkable capability to optima...
10/21/2019 ∙ by Zhe Dong, et al. ∙ 0 ∙ share

read it
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation

Deploying machine learning systems in the real world requires both high ...
06/06/2019 ∙ by Raphael Gontijo Lopes, et al. ∙ 0 ∙ share

read it
Discrete Flows: Invertible Generative Models of Discrete Data

While normalizing flows have led to significant advances in modeling hig...
05/24/2019 ∙ by Dustin Tran, et al. ∙ 6 ∙ share

read it
On Variational Bounds of Mutual Information

Estimating and optimizing Mutual Information (MI) is core to many proble...
05/16/2019 ∙ by Ben Poole, et al. ∙ 8 ∙ share

read it
Preventing Posterior Collapse with delta-VAEs

Due to the phenomenon of "posterior collapse," current latent variable g...
01/10/2019 ∙ by Ali Razavi, et al. ∙ 4 ∙ share

read it
An Information-Theoretic Analysis of Deep Latent-Variable Models

We present an information-theoretic framework for understanding trade-of...
11/01/2017 ∙ by Alexander A. Alemi, et al. ∙ 0 ∙ share

read it
Continual Learning Through Synaptic Intelligence

While deep learning has led to remarkable advances across diverse applic...
03/13/2017 ∙ by Friedemann Zenke, et al. ∙ 0 ∙ share

read it
Survey of Expressivity in Deep Neural Networks

We survey results on neural network expressivity described in "On the Ex...
11/24/2016 ∙ by Maithra Raghu, et al. ∙ 0 ∙ share

read it
Unrolled Generative Adversarial Networks

We introduce a method to stabilize Generative Adversarial Networks (GANs...
11/07/2016 ∙ by Luke Metz, et al. ∙ 0 ∙ share

read it
Categorical Reparameterization with Gumbel-Softmax

Categorical variables are a natural choice for representing discrete str...
11/03/2016 ∙ by Eric Jang, et al. ∙ 0 ∙ share

read it
Exponential expressivity in deep neural networks through transient chaos

We combine Riemannian geometry with the mean field theory of high dimens...
06/16/2016 ∙ by Ben Poole, et al. ∙ 0 ∙ share

read it
On the Expressive Power of Deep Neural Networks

We propose a new approach to the problem of neural network expressivity,...
06/16/2016 ∙ by Maithra Raghu, et al. ∙ 0 ∙ share

read it
Adversarially Learned Inference

We introduce the adversarially learned inference (ALI) model, which join...
06/02/2016 ∙ by Vincent Dumoulin, et al. ∙ 0 ∙ share

read it
The Fast Bilateral Solver

We present the bilateral solver, a novel algorithm for edge-aware smooth...
11/10/2015 ∙ by Jonathan T. Barron, et al. ∙ 0 ∙ share

read it
Analyzing noise in autoencoders and deep networks

Autoencoders have emerged as a useful framework for unsupervised learnin...
06/06/2014 ∙ by Ben Poole, et al. ∙ 0 ∙ share

read it

Ben Poole

Featured Co-authors

Bernhard Schölkopf

Aaron Courville

Stefano Ermon

Cordelia Schmid

Oriol Vinyals

Jascha Sohl-Dickstein

Kevin Murphy

Jon Kleinberg

Surya Ganguli

Chen Sun

Abhishek Kumar

Non-saturating GAN training as divergence minimization

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

What makes for good views for contrastive learning

Using a thousand optimization tasks to learn hyperparameter search strategies

Regularized Autoencoders via Relaxed Injective Probability Flow

Weakly-Supervised Disentanglement Without Compromises

On Implicit Regularization in β-VAEs

Weakly Supervised Disentanglement with Guarantees

On Predictive Information Sub-optimality of RNNs

Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation

Discrete Flows: Invertible Generative Models of Discrete Data

On Variational Bounds of Mutual Information

Preventing Posterior Collapse with delta-VAEs

An Information-Theoretic Analysis of Deep Latent-Variable Models

Continual Learning Through Synaptic Intelligence

Survey of Expressivity in Deep Neural Networks

Unrolled Generative Adversarial Networks

Categorical Reparameterization with Gumbel-Softmax

Exponential expressivity in deep neural networks through transient chaos

On the Expressive Power of Deep Neural Networks

Adversarially Learned Inference

The Fast Bilateral Solver

Analyzing noise in autoencoders and deep networks