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 Andriy Mnih

Andriy Mnih

University College London

Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts


Sep 24, 2021
Wouter Kool, Chris J. Maddison, Andriy Mnih

Figure 1 for Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts
Figure 2 for Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts
Figure 3 for Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts

  Access Paper or Ask Questions

Coupled Gradient Estimators for Discrete Latent Variables


Jun 15, 2021
Zhe Dong, Andriy Mnih, George Tucker

Figure 1 for Coupled Gradient Estimators for Discrete Latent Variables
Figure 2 for Coupled Gradient Estimators for Discrete Latent Variables
Figure 3 for Coupled Gradient Estimators for Discrete Latent Variables
Figure 4 for Coupled Gradient Estimators for Discrete Latent Variables
* Under Review 
  Access Paper or Ask Questions

Generalized Doubly Reparameterized Gradient Estimators


Jan 26, 2021
Matthias Bauer, Andriy Mnih

Figure 1 for Generalized Doubly Reparameterized Gradient Estimators
Figure 2 for Generalized Doubly Reparameterized Gradient Estimators
Figure 3 for Generalized Doubly Reparameterized Gradient Estimators
Figure 4 for Generalized Doubly Reparameterized Gradient Estimators

  Access Paper or Ask Questions

DisARM: An Antithetic Gradient Estimator for Binary Latent Variables


Jun 18, 2020
Zhe Dong, Andriy Mnih, George Tucker

Figure 1 for DisARM: An Antithetic Gradient Estimator for Binary Latent Variables
Figure 2 for DisARM: An Antithetic Gradient Estimator for Binary Latent Variables
Figure 3 for DisARM: An Antithetic Gradient Estimator for Binary Latent Variables
Figure 4 for DisARM: An Antithetic Gradient Estimator for Binary Latent Variables

  Access Paper or Ask Questions

The Lipschitz Constant of Self-Attention


Jun 08, 2020
Hyunjik Kim, George Papamakarios, Andriy Mnih

Figure 1 for The Lipschitz Constant of Self-Attention
Figure 2 for The Lipschitz Constant of Self-Attention
Figure 3 for The Lipschitz Constant of Self-Attention
Figure 4 for The Lipschitz Constant of Self-Attention

  Access Paper or Ask Questions

Q-Learning in enormous action spaces via amortized approximate maximization


Jan 22, 2020
Tom Van de Wiele, David Warde-Farley, Andriy Mnih, Volodymyr Mnih

Figure 1 for Q-Learning in enormous action spaces via amortized approximate maximization
Figure 2 for Q-Learning in enormous action spaces via amortized approximate maximization
Figure 3 for Q-Learning in enormous action spaces via amortized approximate maximization
Figure 4 for Q-Learning in enormous action spaces via amortized approximate maximization
* A previous version of this work appeared at the Deep Reinforcement Learning Workshop, NeurIPS 2018 
  Access Paper or Ask Questions

Sparse Orthogonal Variational Inference for Gaussian Processes


Oct 24, 2019
Jiaxin Shi, Michalis K. Titsias, Andriy Mnih

Figure 1 for Sparse Orthogonal Variational Inference for Gaussian Processes
Figure 2 for Sparse Orthogonal Variational Inference for Gaussian Processes
Figure 3 for Sparse Orthogonal Variational Inference for Gaussian Processes
Figure 4 for Sparse Orthogonal Variational Inference for Gaussian Processes

  Access Paper or Ask Questions

Monte Carlo Gradient Estimation in Machine Learning


Jun 25, 2019
Shakir Mohamed, Mihaela Rosca, Michael Figurnov, Andriy Mnih

Figure 1 for Monte Carlo Gradient Estimation in Machine Learning
Figure 2 for Monte Carlo Gradient Estimation in Machine Learning
Figure 3 for Monte Carlo Gradient Estimation in Machine Learning
Figure 4 for Monte Carlo Gradient Estimation in Machine Learning
* 59 pages, under review 
  Access Paper or Ask Questions

Attentive Neural Processes


Jan 17, 2019
Hyunjik Kim, Andriy Mnih, Jonathan Schwarz, Marta Garnelo, Ali Eslami, Dan Rosenbaum, Oriol Vinyals, Yee Whye Teh

Figure 1 for Attentive Neural Processes
Figure 2 for Attentive Neural Processes
Figure 3 for Attentive Neural Processes
Figure 4 for Attentive Neural Processes

  Access Paper or Ask Questions

Implicit Reparameterization Gradients


Nov 01, 2018
Michael Figurnov, Shakir Mohamed, Andriy Mnih

Figure 1 for Implicit Reparameterization Gradients
Figure 2 for Implicit Reparameterization Gradients
Figure 3 for Implicit Reparameterization Gradients
Figure 4 for Implicit Reparameterization Gradients
* NIPS 2018 
  Access Paper or Ask Questions

Resampled Priors for Variational Autoencoders


Oct 26, 2018
Matthias Bauer, Andriy Mnih

Figure 1 for Resampled Priors for Variational Autoencoders
Figure 2 for Resampled Priors for Variational Autoencoders
Figure 3 for Resampled Priors for Variational Autoencoders
Figure 4 for Resampled Priors for Variational Autoencoders

  Access Paper or Ask Questions

Disentangling by Factorising


Jun 06, 2018
Hyunjik Kim, Andriy Mnih

Figure 1 for Disentangling by Factorising
Figure 2 for Disentangling by Factorising
Figure 3 for Disentangling by Factorising
Figure 4 for Disentangling by Factorising
* Shorter version appeared in Learning Disentangled Representations: From Perception to Control workshop at NIPS, 2017: https://sites.google.com/corp/view/disentanglenips2017 
  Access Paper or Ask Questions

Filtering Variational Objectives


Nov 12, 2017
Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Mohammad Norouzi, Andriy Mnih, Arnaud Doucet, Yee Whye Teh

Figure 1 for Filtering Variational Objectives
Figure 2 for Filtering Variational Objectives
Figure 3 for Filtering Variational Objectives
Figure 4 for Filtering Variational Objectives

  Access Paper or Ask Questions

REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models


Nov 06, 2017
George Tucker, Andriy Mnih, Chris J. Maddison, Dieterich Lawson, Jascha Sohl-Dickstein

Figure 1 for REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models
Figure 2 for REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models
Figure 3 for REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models
* NIPS 2017 
  Access Paper or Ask Questions

Variational Memory Addressing in Generative Models


Sep 21, 2017
Jörg Bornschein, Andriy Mnih, Daniel Zoran, Danilo J. Rezende

Figure 1 for Variational Memory Addressing in Generative Models
Figure 2 for Variational Memory Addressing in Generative Models
Figure 3 for Variational Memory Addressing in Generative Models
Figure 4 for Variational Memory Addressing in Generative Models

  Access Paper or Ask Questions

Particle Value Functions


Mar 16, 2017
Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Arnaud Doucet, Andriy Mnih, Yee Whye Teh

Figure 1 for Particle Value Functions
Figure 2 for Particle Value Functions
Figure 3 for Particle Value Functions
Figure 4 for Particle Value Functions

  Access Paper or Ask Questions

The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables


Mar 05, 2017
Chris J. Maddison, Andriy Mnih, Yee Whye Teh

Figure 1 for The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
Figure 2 for The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
Figure 3 for The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
Figure 4 for The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables

  Access Paper or Ask Questions

Variational inference for Monte Carlo objectives


Jun 01, 2016
Andriy Mnih, Danilo J. Rezende

Figure 1 for Variational inference for Monte Carlo objectives
Figure 2 for Variational inference for Monte Carlo objectives
Figure 3 for Variational inference for Monte Carlo objectives
Figure 4 for Variational inference for Monte Carlo objectives
* Appears in Proceedings of the 33rd International Conference on Machine Learning (ICML), New York, NY, USA, 2016. JMLR: W&CP volume 48 
  Access Paper or Ask Questions

MuProp: Unbiased Backpropagation for Stochastic Neural Networks


Feb 25, 2016
Shixiang Gu, Sergey Levine, Ilya Sutskever, Andriy Mnih

Figure 1 for MuProp: Unbiased Backpropagation for Stochastic Neural Networks
Figure 2 for MuProp: Unbiased Backpropagation for Stochastic Neural Networks
Figure 3 for MuProp: Unbiased Backpropagation for Stochastic Neural Networks
Figure 4 for MuProp: Unbiased Backpropagation for Stochastic Neural Networks
* Published as a conference paper at ICLR 2016 
  Access Paper or Ask Questions

Neural Variational Inference and Learning in Belief Networks


Jun 04, 2014
Andriy Mnih, Karol Gregor

Figure 1 for Neural Variational Inference and Learning in Belief Networks
* Proceedings of the 31st International Conference on Machine Learning (ICML), JMLR: W&CP volume 32, 2014 pgs 1791-1799 
  Access Paper or Ask Questions

Deep AutoRegressive Networks


May 20, 2014
Karol Gregor, Ivo Danihelka, Andriy Mnih, Charles Blundell, Daan Wierstra

Figure 1 for Deep AutoRegressive Networks
Figure 2 for Deep AutoRegressive Networks
Figure 3 for Deep AutoRegressive Networks
Figure 4 for Deep AutoRegressive Networks
* Karol Gregor, Ivo Danihelka, Andriy Mnih, Charles Blundell, Daan Wierstra. Deep AutoRegressive Networks. In Proceedings of the 31st International Conference on Machine Learning (ICML), JMLR: W&CP volume 32, 2014 
 * Appears in Proceedings of the 31st International Conference on Machine Learning (ICML), Beijing, China, 2014 
  Access Paper or Ask Questions

A Fast and Simple Algorithm for Training Neural Probabilistic Language Models


Jun 27, 2012
Andriy Mnih, Yee Whye Teh

Figure 1 for A Fast and Simple Algorithm for Training Neural Probabilistic Language Models
Figure 2 for A Fast and Simple Algorithm for Training Neural Probabilistic Language Models
Figure 3 for A Fast and Simple Algorithm for Training Neural Probabilistic Language Models
* In Proceedings of the 29th International Conference on Machine Learning, pages 1751-1758, 2012 
 * Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012) 
  Access Paper or Ask Questions

Learning Item Trees for Probabilistic Modelling of Implicit Feedback


Sep 27, 2011
Andriy Mnih, Yee Whye Teh

Figure 1 for Learning Item Trees for Probabilistic Modelling of Implicit Feedback
Figure 2 for Learning Item Trees for Probabilistic Modelling of Implicit Feedback
* 8 pages 
  Access Paper or Ask Questions