83.4k citations · 107.7k across the 29 of their papers we have counts for
9 papers · 1 filter
On Linear Identifiability of Learned Representations
Geoffrey Roeder, Luke Metz, Diederik P. Kingma
Identifiability is a desirable property of a statistical model: it implies that the true model parameters may be estimated to any desired precision, given sufficient computational…
ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA
Ilyes Khemakhem, Ricardo Pio Monti, Diederik P. Kingma +1
We consider the identifiability theory of probabilistic models and establish sufficient conditions under which the representations learned by a very broad family of conditional ene…
Flow Contrastive Estimation of Energy-Based Models
Ruiqi Gao, Erik Nijkamp, Diederik P. Kingma +3
This paper studies a training method to jointly estimate an energy-based model and a flow-based model, in which the two models are iteratively updated based on a shared adversarial…
Variational Autoencoders and Nonlinear ICA: A Unifying Framework
Ilyes Khemakhem, Diederik P. Kingma, Ricardo Pio Monti +1
The framework of variational autoencoders allows us to efficiently learn deep latent-variable models, such that the model's marginal distribution over observed variables fits the d…
Glow: Generative Flow with Invertible 1x1 Convolutions
Diederik P. Kingma, Prafulla Dhariwal
Flow-based generative models (Dinh et al., 2014) are conceptually attractive due to tractability of the exact log-likelihood, tractability of exact latent-variable inference, and p…
Learning Sparse Neural Networks through Regularization
Christos Louizos, Max Welling, Diederik P. Kingma
We propose a practical method for norm regularization for neural networks: pruning the network during training by encouraging weights to become exactly zero. Such regularizat…
Variational Dropout and the Local Reparameterization Trick
Diederik P. Kingma, Tim Salimans, Max Welling
We investigate a local reparameterizaton technique for greatly reducing the variance of stochastic gradients for variational Bayesian inference (SGVB) of a posterior over model par…
Variational Recurrent Auto-Encoders
Otto Fabius, Joost R. van Amersfoort
In this paper we propose a model that combines the strengths of RNNs and SGVB: the Variational Recurrent Auto-Encoder (VRAE). Such a model can be used for efficient, large scale un…
Auto-Encoding Variational Bayes
Diederik P Kingma, Max Welling
How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and l…