7.4k citations · 24.2k across the 136 of their papers we have counts for
23 papers · 1 filter
Neural Approximate Sufficient Statistics for Implicit Models
Yanzhi Chen, Dinghuai Zhang, Michael Gutmann +2
We consider the fundamental problem of how to automatically construct summary statistics for implicit generative models where the evaluation of the likelihood function is intractab…
On the Spectral Bias of Neural Networks
Nasim Rahaman, Aristide Baratin, Devansh Arpit +5
Neural networks are known to be a class of highly expressive functions able to fit even random input-output mappings with accuracy. In this work, we present properties of n…
Manifold Mixup: Better Representations by Interpolating Hidden States
Vikas Verma, Alex Lamb, Christopher Beckham +5
Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly different test examples. This includes di…
Hierarchical Adversarially Learned Inference
Mohamed Ishmael Belghazi, Sai Rajeswar, Olivier Mastropietro +3
We propose a novel hierarchical generative model with a simple Markovian structure and a corresponding inference model. Both the generative and inference model are trained using th…
GibbsNet: Iterative Adversarial Inference for Deep Graphical Models
Alex Lamb, Devon Hjelm, Yaroslav Ganin +3
Directed latent variable models that formulate the joint distribution as have the advantage of fast and exact sampling. However, these models have the w…
Bayesian Hypernetworks
David Krueger, Chin-Wei Huang, Riashat Islam +3
We study Bayesian hypernetworks: a framework for approximate Bayesian inference in neural networks. A Bayesian hypernetwork $\h$ is a neural network which learns to transform a sim…