Diederik P. Kingma | DeepAI

DeepAI AI Chat

Featured Co-authors

Xi Chen
275 publications
Pieter Abbeel
255 publications
Stefano Ermon
165 publications
Max Welling
164 publications
Mohammad Norouzi
70 publications
Ilya Sutskever
53 publications
Ying Nian Wu
53 publications
Aapo Hyvärinen
42 publications
Tim Salimans
36 publications
William Chan
36 publications
Andrew M. Dai
34 publications

∙ 03/01/2023

Understanding the Diffusion Objective as a Weighted Integral of ELBOs

Diffusion models in the literature are optimized with various objectives...

3 Diederik P. Kingma, et al. ∙

∙ 10/06/2022

On Distillation of Guided Diffusion Models

Classifier-free guided diffusion models have recently been shown to be h...

12 Chenlin Meng, et al. ∙

∙ 10/05/2022

Imagen Video: High Definition Video Generation with Diffusion Models

We present Imagen Video, a text-conditional video generation system base...

16 Jonathan Ho, et al. ∙

∙ 07/01/2021

Variational Diffusion Models

Diffusion-based generative models have demonstrated a capacity for perce...

7 Diederik P. Kingma, et al. ∙

∙ 11/06/2020

Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesis

We describe a sequence-to-sequence neural network which can directly gen...

0 Ron J. Weiss, et al. ∙

∙ 07/01/2020

On Linear Identifiability of Learned Representations

Identifiability is a desirable property of a statistical model: it impli...

3 Geoffrey Roeder, et al. ∙

∙ 02/26/2020

ICE-BeeM: Identifiable Conditional Energy-Based Deep Models

Despite the growing popularity of energy-based models, their identifiabi...

6 Ilyes Khemakhem, et al. ∙

∙ 12/02/2019

Flow Contrastive Estimation of Energy-Based Models

This paper studies a training method to jointly estimate an energy-based...

43 Ruiqi Gao, et al. ∙

∙ 07/10/2019

Variational Autoencoders and Nonlinear ICA: A Unifying Framework

The framework of variational autoencoders allows us to efficiently learn...

2 Ilyes Khemakhem, et al. ∙

∙ 06/06/2019

An Introduction to Variational Autoencoders

Variational autoencoders provide a principled framework for learning dee...

0 Diederik P. Kingma, et al. ∙

∙ 07/09/2018

Glow: Generative Flow with Invertible 1x1 Convolutions

Flow-based generative models (Dinh et al., 2014) are conceptually attrac...

2 Diederik P. Kingma, et al. ∙

∙ 12/04/2017

Learning Sparse Neural Networks through L_0 Regularization

We propose a practical method for L_0 norm regularization for neural net...

0 Christos Louizos, et al. ∙

∙ 01/19/2017

PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications

PixelCNNs are a recently proposed class of powerful generative models wi...

0 Tim Salimans, et al. ∙

∙ 11/08/2016

Variational Lossy Autoencoder

Representation learning seeks to expose certain aspects of observed data...

0 Xi Chen, et al. ∙

∙ 06/15/2016

Improving Variational Inference with Inverse Autoregressive Flow

The framework of normalizing flows provides a general strategy for flexi...

0 Diederik P. Kingma, et al. ∙

∙ 02/25/2016

Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks

We present weight normalization: a reparameterization of the weight vect...

0 Tim Salimans, et al. ∙

∙ 06/08/2015

Variational Dropout and the Local Reparameterization Trick

We investigate a local reparameterizaton technique for greatly reducing ...

0 Diederik P. Kingma, et al. ∙

∙ 10/23/2014

Markov Chain Monte Carlo and Variational Inference: Bridging the Gap

Recent advances in stochastic gradient variational inference have made i...

0 Tim Salimans, et al. ∙

∙ 02/03/2014

Efficient Gradient-Based Inference through Transformations between Bayes Nets and Neural Nets

Hierarchical Bayesian networks and neural networks with stochastic hidde...

0 Diederik P. Kingma, et al. ∙

∙ 12/20/2013

Auto-Encoding Variational Bayes

How can we perform efficient inference and learning in directed probabil...

0 Diederik P. Kingma, et al. ∙

∙ 06/04/2013

Fast Gradient-Based Inference with Continuous Latent Variable Models in Auxiliary Form

We propose a technique for increasing the efficiency of gradient-based i...

0 Diederik P. Kingma, et al. ∙