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 Michalis K. Titsias

Michalis K. Titsias

Sequential Changepoint Detection in Neural Networks with Checkpoints


Oct 06, 2020
Michalis K. Titsias, Jakub Sygnowski, Yutian Chen

Figure 1 for Sequential Changepoint Detection in Neural Networks with Checkpoints
Figure 2 for Sequential Changepoint Detection in Neural Networks with Checkpoints
Figure 3 for Sequential Changepoint Detection in Neural Networks with Checkpoints
Figure 4 for Sequential Changepoint Detection in Neural Networks with Checkpoints
* 17 pages, 7 figures 
  Access Paper or Ask Questions

Information Theoretic Meta Learning with Gaussian Processes


Oct 05, 2020
Michalis K. Titsias, Sotirios Nikoloutsopoulos, Alexandre Galashov

Figure 1 for Information Theoretic Meta Learning with Gaussian Processes
Figure 2 for Information Theoretic Meta Learning with Gaussian Processes
Figure 3 for Information Theoretic Meta Learning with Gaussian Processes
Figure 4 for Information Theoretic Meta Learning with Gaussian Processes
* 26 pages, 5 figures 
  Access Paper or Ask Questions

Unbiased Gradient Estimation for Variational Auto-Encoders using Coupled Markov Chains


Oct 05, 2020
Francisco J. R. Ruiz, Michalis K. Titsias, Taylan Cemgil, Arnaud Doucet

Figure 1 for Unbiased Gradient Estimation for Variational Auto-Encoders using Coupled Markov Chains
Figure 2 for Unbiased Gradient Estimation for Variational Auto-Encoders using Coupled Markov Chains
Figure 3 for Unbiased Gradient Estimation for Variational Auto-Encoders using Coupled Markov Chains
Figure 4 for Unbiased Gradient Estimation for Variational Auto-Encoders using Coupled Markov Chains
* 16 pages, 4 figures 
  Access Paper or Ask Questions

Gradient-based Adaptive Markov Chain Monte Carlo


Nov 04, 2019
Michalis K. Titsias, Petros Dellaportas

Figure 1 for Gradient-based Adaptive Markov Chain Monte Carlo
Figure 2 for Gradient-based Adaptive Markov Chain Monte Carlo
Figure 3 for Gradient-based Adaptive Markov Chain Monte Carlo
Figure 4 for Gradient-based Adaptive Markov Chain Monte Carlo
* 17 pages, 7 Figures, NeurIPS 2019 
  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

Prescribed Generative Adversarial Networks


Oct 09, 2019
Adji B. Dieng, Francisco J. R. Ruiz, David M. Blei, Michalis K. Titsias

Figure 1 for Prescribed Generative Adversarial Networks
Figure 2 for Prescribed Generative Adversarial Networks
Figure 3 for Prescribed Generative Adversarial Networks
Figure 4 for Prescribed Generative Adversarial Networks
* Code for this paper can be found at https://github.com/adjidieng/PresGANs 
  Access Paper or Ask Questions

A Contrastive Divergence for Combining Variational Inference and MCMC


May 28, 2019
Francisco J. R. Ruiz, Michalis K. Titsias

Figure 1 for A Contrastive Divergence for Combining Variational Inference and MCMC
Figure 2 for A Contrastive Divergence for Combining Variational Inference and MCMC
Figure 3 for A Contrastive Divergence for Combining Variational Inference and MCMC
Figure 4 for A Contrastive Divergence for Combining Variational Inference and MCMC
* International Conference on Machine Learning (ICML 2019). 12 pages, 3 figures 
  Access Paper or Ask Questions

Functional Regularisation for Continual Learning using Gaussian Processes


Jan 31, 2019
Michalis K. Titsias, Jonathan Schwarz, Alexander G. de G. Matthews, Razvan Pascanu, Yee Whye Teh

Figure 1 for Functional Regularisation for Continual Learning using Gaussian Processes
Figure 2 for Functional Regularisation for Continual Learning using Gaussian Processes
Figure 3 for Functional Regularisation for Continual Learning using Gaussian Processes
Figure 4 for Functional Regularisation for Continual Learning using Gaussian Processes

  Access Paper or Ask Questions

Unbiased Implicit Variational Inference


Oct 10, 2018
Michalis K. Titsias, Francisco J. R. Ruiz

Figure 1 for Unbiased Implicit Variational Inference
Figure 2 for Unbiased Implicit Variational Inference
Figure 3 for Unbiased Implicit Variational Inference
Figure 4 for Unbiased Implicit Variational Inference
* 9 pages, 3 figures 
  Access Paper or Ask Questions

Bayesian Transfer Reinforcement Learning with Prior Knowledge Rules


Sep 30, 2018
Michalis K. Titsias, Sotirios Nikoloutsopoulos

Figure 1 for Bayesian Transfer Reinforcement Learning with Prior Knowledge Rules
Figure 2 for Bayesian Transfer Reinforcement Learning with Prior Knowledge Rules
* 11 pages, 2 figures 
  Access Paper or Ask Questions

Fully Scalable Gaussian Processes using Subspace Inducing Inputs


Jul 12, 2018
Aristeidis Panos, Petros Dellaportas, Michalis K. Titsias

Figure 1 for Fully Scalable Gaussian Processes using Subspace Inducing Inputs
Figure 2 for Fully Scalable Gaussian Processes using Subspace Inducing Inputs
Figure 3 for Fully Scalable Gaussian Processes using Subspace Inducing Inputs
Figure 4 for Fully Scalable Gaussian Processes using Subspace Inducing Inputs

  Access Paper or Ask Questions

Augment and Reduce: Stochastic Inference for Large Categorical Distributions


Jun 07, 2018
Francisco J. R. Ruiz, Michalis K. Titsias, Adji B. Dieng, David M. Blei

Figure 1 for Augment and Reduce: Stochastic Inference for Large Categorical Distributions
Figure 2 for Augment and Reduce: Stochastic Inference for Large Categorical Distributions
Figure 3 for Augment and Reduce: Stochastic Inference for Large Categorical Distributions
Figure 4 for Augment and Reduce: Stochastic Inference for Large Categorical Distributions
* Francisco J. R. Ruiz, Michalis K. Titsias, Adji B. Dieng, and David M. Blei. Augment and Reduce: Stochastic Inference for Large Categorical Distributions. International Conference on Machine Learning. Stockholm (Sweden), July 2018 
 * 11 pages, 2 figures 
  Access Paper or Ask Questions

Auxiliary gradient-based sampling algorithms


Jan 25, 2018
Michalis K. Titsias, Omiros Papaspiliopoulos

Figure 1 for Auxiliary gradient-based sampling algorithms
Figure 2 for Auxiliary gradient-based sampling algorithms
Figure 3 for Auxiliary gradient-based sampling algorithms
Figure 4 for Auxiliary gradient-based sampling algorithms
* 41 pages, 8 figures, 11 tables, To appear in Journal of the Royal Statistical Society: Series B 
  Access Paper or Ask Questions

Learning Model Reparametrizations: Implicit Variational Inference by Fitting MCMC distributions


Aug 04, 2017
Michalis K. Titsias

Figure 1 for Learning Model Reparametrizations: Implicit Variational Inference by Fitting MCMC distributions
Figure 2 for Learning Model Reparametrizations: Implicit Variational Inference by Fitting MCMC distributions
Figure 3 for Learning Model Reparametrizations: Implicit Variational Inference by Fitting MCMC distributions
Figure 4 for Learning Model Reparametrizations: Implicit Variational Inference by Fitting MCMC distributions
* 16 pages, 6 figures 
  Access Paper or Ask Questions

Bayesian Boolean Matrix Factorisation


Feb 25, 2017
Tammo Rukat, Chris C. Holmes, Michalis K. Titsias, Christopher Yau

Figure 1 for Bayesian Boolean Matrix Factorisation
Figure 2 for Bayesian Boolean Matrix Factorisation
Figure 3 for Bayesian Boolean Matrix Factorisation
Figure 4 for Bayesian Boolean Matrix Factorisation

  Access Paper or Ask Questions

One-vs-Each Approximation to Softmax for Scalable Estimation of Probabilities


Oct 29, 2016
Michalis K. Titsias

Figure 1 for One-vs-Each Approximation to Softmax for Scalable Estimation of Probabilities
Figure 2 for One-vs-Each Approximation to Softmax for Scalable Estimation of Probabilities
Figure 3 for One-vs-Each Approximation to Softmax for Scalable Estimation of Probabilities
Figure 4 for One-vs-Each Approximation to Softmax for Scalable Estimation of Probabilities
* To appear in NIPS 2016 
  Access Paper or Ask Questions

The Generalized Reparameterization Gradient


Oct 19, 2016
Francisco J. R. Ruiz, Michalis K. Titsias, David M. Blei

Figure 1 for The Generalized Reparameterization Gradient
Figure 2 for The Generalized Reparameterization Gradient
Figure 3 for The Generalized Reparameterization Gradient
Figure 4 for The Generalized Reparameterization Gradient
* 16 pages, 15 figures, NIPS version 
  Access Paper or Ask Questions

Overdispersed Black-Box Variational Inference


Mar 03, 2016
Francisco J. R. Ruiz, Michalis K. Titsias, David M. Blei

Figure 1 for Overdispersed Black-Box Variational Inference
* 10 pages, 6 figures 
  Access Paper or Ask Questions

Inference for determinantal point processes without spectral knowledge


Jul 04, 2015
Rémi Bardenet, Michalis K. Titsias

Figure 1 for Inference for determinantal point processes without spectral knowledge
Figure 2 for Inference for determinantal point processes without spectral knowledge
Figure 3 for Inference for determinantal point processes without spectral knowledge
Figure 4 for Inference for determinantal point processes without spectral knowledge

  Access Paper or Ask Questions

Local Expectation Gradients for Doubly Stochastic Variational Inference


Mar 04, 2015
Michalis K. Titsias

Figure 1 for Local Expectation Gradients for Doubly Stochastic Variational Inference
Figure 2 for Local Expectation Gradients for Doubly Stochastic Variational Inference
Figure 3 for Local Expectation Gradients for Doubly Stochastic Variational Inference
Figure 4 for Local Expectation Gradients for Doubly Stochastic Variational Inference

  Access Paper or Ask Questions

Variational Inference for Uncertainty on the Inputs of Gaussian Process Models


Sep 08, 2014
Andreas C. Damianou, Michalis K. Titsias, Neil D. Lawrence

Figure 1 for Variational Inference for Uncertainty on the Inputs of Gaussian Process Models
Figure 2 for Variational Inference for Uncertainty on the Inputs of Gaussian Process Models
Figure 3 for Variational Inference for Uncertainty on the Inputs of Gaussian Process Models
Figure 4 for Variational Inference for Uncertainty on the Inputs of Gaussian Process Models
* 51 pages (of which 10 is Appendix), 19 figures 
  Access Paper or Ask Questions

Statistical Inference in Hidden Markov Models using $k$-segment Constraints


Nov 05, 2013
Michalis K. Titsias, Christopher Yau, Christopher C. Holmes

Figure 1 for Statistical Inference in Hidden Markov Models using $k$-segment Constraints
Figure 2 for Statistical Inference in Hidden Markov Models using $k$-segment Constraints
Figure 3 for Statistical Inference in Hidden Markov Models using $k$-segment Constraints
Figure 4 for Statistical Inference in Hidden Markov Models using $k$-segment Constraints
* 37 pages 
  Access Paper or Ask Questions

Variational Gaussian Process Dynamical Systems


Jul 25, 2011
Andreas C. Damianou, Michalis K. Titsias, Neil D. Lawrence

Figure 1 for Variational Gaussian Process Dynamical Systems
Figure 2 for Variational Gaussian Process Dynamical Systems
Figure 3 for Variational Gaussian Process Dynamical Systems
Figure 4 for Variational Gaussian Process Dynamical Systems
* 16 pages, 19 figures 
  Access Paper or Ask Questions

Variational Inducing Kernels for Sparse Convolved Multiple Output Gaussian Processes


Dec 16, 2009
Mauricio A. Álvarez, David Luengo, Michalis K. Titsias, Neil D. Lawrence

Figure 1 for Variational Inducing Kernels for Sparse Convolved Multiple Output Gaussian Processes
Figure 2 for Variational Inducing Kernels for Sparse Convolved Multiple Output Gaussian Processes
Figure 3 for Variational Inducing Kernels for Sparse Convolved Multiple Output Gaussian Processes
Figure 4 for Variational Inducing Kernels for Sparse Convolved Multiple Output Gaussian Processes
* Technical report, 22 pages, 8 figures 
  Access Paper or Ask Questions