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 Maurizio Filippone

Maurizio Filippone

A Unified View of Stochastic Hamiltonian Sampling


Jun 30, 2021
Giulio Franzese, Dimitrios Milios, Maurizio Filippone, Pietro Michiardi

Figure 1 for A Unified View of Stochastic Hamiltonian Sampling
Figure 2 for A Unified View of Stochastic Hamiltonian Sampling
Figure 3 for A Unified View of Stochastic Hamiltonian Sampling
Figure 4 for A Unified View of Stochastic Hamiltonian Sampling

  Access Paper or Ask Questions

Model Selection for Bayesian Autoencoders


Jun 11, 2021
Ba-Hien Tran, Simone Rossi, Dimitrios Milios, Pietro Michiardi, Edwin V. Bonilla, Maurizio Filippone

Figure 1 for Model Selection for Bayesian Autoencoders
Figure 2 for Model Selection for Bayesian Autoencoders
Figure 3 for Model Selection for Bayesian Autoencoders
Figure 4 for Model Selection for Bayesian Autoencoders

  Access Paper or Ask Questions

All You Need is a Good Functional Prior for Bayesian Deep Learning


Nov 25, 2020
Ba-Hien Tran, Simone Rossi, Dimitrios Milios, Maurizio Filippone

Figure 1 for All You Need is a Good Functional Prior for Bayesian Deep Learning
Figure 2 for All You Need is a Good Functional Prior for Bayesian Deep Learning
Figure 3 for All You Need is a Good Functional Prior for Bayesian Deep Learning
Figure 4 for All You Need is a Good Functional Prior for Bayesian Deep Learning

  Access Paper or Ask Questions

Sparse within Sparse Gaussian Processes using Neighbor Information


Nov 12, 2020
Gia-Lac Tran, Dimitrios Milios, Pietro Michiardi, Maurizio Filippone

Figure 1 for Sparse within Sparse Gaussian Processes using Neighbor Information
Figure 2 for Sparse within Sparse Gaussian Processes using Neighbor Information
Figure 3 for Sparse within Sparse Gaussian Processes using Neighbor Information
Figure 4 for Sparse within Sparse Gaussian Processes using Neighbor Information
* 10 pages 
  Access Paper or Ask Questions

Learning Optimal Conditional Priors For Disentangled Representations


Oct 19, 2020
Graziano Mita, Maurizio Filippone, Pietro Michiardi

Figure 1 for Learning Optimal Conditional Priors For Disentangled Representations
Figure 2 for Learning Optimal Conditional Priors For Disentangled Representations
Figure 3 for Learning Optimal Conditional Priors For Disentangled Representations
Figure 4 for Learning Optimal Conditional Priors For Disentangled Representations

  Access Paper or Ask Questions

Isotropic SGD: a Practical Approach to Bayesian Posterior Sampling


Jun 09, 2020
Giulio Franzese, Rosa Candela, Dimitrios Milios, Maurizio Filippone, Pietro Michiardi

Figure 1 for Isotropic SGD: a Practical Approach to Bayesian Posterior Sampling
Figure 2 for Isotropic SGD: a Practical Approach to Bayesian Posterior Sampling
Figure 3 for Isotropic SGD: a Practical Approach to Bayesian Posterior Sampling
Figure 4 for Isotropic SGD: a Practical Approach to Bayesian Posterior Sampling

  Access Paper or Ask Questions

A Variational View on Bootstrap Ensembles as Bayesian Inference


Jun 08, 2020
Dimitrios Milios, Pietro Michiardi, Maurizio Filippone

Figure 1 for A Variational View on Bootstrap Ensembles as Bayesian Inference
Figure 2 for A Variational View on Bootstrap Ensembles as Bayesian Inference
Figure 3 for A Variational View on Bootstrap Ensembles as Bayesian Inference
Figure 4 for A Variational View on Bootstrap Ensembles as Bayesian Inference

  Access Paper or Ask Questions

Rethinking Sparse Gaussian Processes: Bayesian Approaches to Inducing-Variable Approximations


Mar 09, 2020
Simone Rossi, Markus Heinonen, Edwin V. Bonilla, Zheyang Shen, Maurizio Filippone

Figure 1 for Rethinking Sparse Gaussian Processes: Bayesian Approaches to Inducing-Variable Approximations
Figure 2 for Rethinking Sparse Gaussian Processes: Bayesian Approaches to Inducing-Variable Approximations
Figure 3 for Rethinking Sparse Gaussian Processes: Bayesian Approaches to Inducing-Variable Approximations
Figure 4 for Rethinking Sparse Gaussian Processes: Bayesian Approaches to Inducing-Variable Approximations

  Access Paper or Ask Questions

Kernel computations from large-scale random features obtained by Optical Processing Units


Dec 02, 2019
Ruben Ohana, Jonas Wacker, Jonathan Dong, Sébastien Marmin, Florent Krzakala, Maurizio Filippone, Laurent Daudet

Figure 1 for Kernel computations from large-scale random features obtained by Optical Processing Units
Figure 2 for Kernel computations from large-scale random features obtained by Optical Processing Units
Figure 3 for Kernel computations from large-scale random features obtained by Optical Processing Units
Figure 4 for Kernel computations from large-scale random features obtained by Optical Processing Units
* 5 pages, 3 figures, submitted to ICASSP 2020 
  Access Paper or Ask Questions

Efficient Approximate Inference with Walsh-Hadamard Variational Inference


Nov 29, 2019
Simone Rossi, Sebastien Marmin, Maurizio Filippone

Figure 1 for Efficient Approximate Inference with Walsh-Hadamard Variational Inference
Figure 2 for Efficient Approximate Inference with Walsh-Hadamard Variational Inference
Figure 3 for Efficient Approximate Inference with Walsh-Hadamard Variational Inference
* Paper accepted at the 4th Workshop on Bayesian Deep Learning (NeurIPS 2019), Vancouver, Canada. arXiv admin note: substantial text overlap with arXiv:1905.11248 
  Access Paper or Ask Questions

LIBRE: Learning Interpretable Boolean Rule Ensembles


Nov 15, 2019
Graziano Mita, Paolo Papotti, Maurizio Filippone, Pietro Michiardi

Figure 1 for LIBRE: Learning Interpretable Boolean Rule Ensembles
Figure 2 for LIBRE: Learning Interpretable Boolean Rule Ensembles
Figure 3 for LIBRE: Learning Interpretable Boolean Rule Ensembles
Figure 4 for LIBRE: Learning Interpretable Boolean Rule Ensembles

  Access Paper or Ask Questions

Sparsification as a Remedy for Staleness in Distributed Asynchronous SGD


Oct 21, 2019
Rosa Candela, Giulio Franzese, Maurizio Filippone, Pietro Michiardi

Figure 1 for Sparsification as a Remedy for Staleness in Distributed Asynchronous SGD
Figure 2 for Sparsification as a Remedy for Staleness in Distributed Asynchronous SGD
Figure 3 for Sparsification as a Remedy for Staleness in Distributed Asynchronous SGD
Figure 4 for Sparsification as a Remedy for Staleness in Distributed Asynchronous SGD

  Access Paper or Ask Questions

Deep Compositional Spatial Models


Jun 06, 2019
Andrew Zammit-Mangion, Tin Lok James Ng, Quan Vu, Maurizio Filippone

Figure 1 for Deep Compositional Spatial Models
Figure 2 for Deep Compositional Spatial Models
Figure 3 for Deep Compositional Spatial Models
Figure 4 for Deep Compositional Spatial Models
* 57 pages, 11 figures 
  Access Paper or Ask Questions

Walsh-Hadamard Variational Inference for Bayesian Deep Learning


May 27, 2019
Simone Rossi, Sebastien Marmin, Maurizio Filippone

Figure 1 for Walsh-Hadamard Variational Inference for Bayesian Deep Learning
Figure 2 for Walsh-Hadamard Variational Inference for Bayesian Deep Learning
Figure 3 for Walsh-Hadamard Variational Inference for Bayesian Deep Learning
Figure 4 for Walsh-Hadamard Variational Inference for Bayesian Deep Learning

  Access Paper or Ask Questions

A comparative evaluation of novelty detection algorithms for discrete sequences


Feb 28, 2019
Rémi Domingues, Pietro Michiardi, Jérémie Barlet, Maurizio Filippone

Figure 1 for A comparative evaluation of novelty detection algorithms for discrete sequences
Figure 2 for A comparative evaluation of novelty detection algorithms for discrete sequences
Figure 3 for A comparative evaluation of novelty detection algorithms for discrete sequences
Figure 4 for A comparative evaluation of novelty detection algorithms for discrete sequences
* Submitted to Artificial Intelligence Review journal; 24 pages, 4 tables, 11 figures 
  Access Paper or Ask Questions

Variational Calibration of Computer Models


Oct 29, 2018
Sébastien Marmin, Maurizio Filippone

Figure 1 for Variational Calibration of Computer Models
Figure 2 for Variational Calibration of Computer Models
Figure 3 for Variational Calibration of Computer Models
Figure 4 for Variational Calibration of Computer Models

  Access Paper or Ask Questions

Good Initializations of Variational Bayes for Deep Models


Oct 18, 2018
Simone Rossi, Pietro Michiardi, Maurizio Filippone

Figure 1 for Good Initializations of Variational Bayes for Deep Models
Figure 2 for Good Initializations of Variational Bayes for Deep Models
Figure 3 for Good Initializations of Variational Bayes for Deep Models
Figure 4 for Good Initializations of Variational Bayes for Deep Models
* 8 pages of main paper (+2 for references and +5 of supplement material) 
  Access Paper or Ask Questions

Constraining the Dynamics of Deep Probabilistic Models


Jun 18, 2018
Marco Lorenzi, Maurizio Filippone

Figure 1 for Constraining the Dynamics of Deep Probabilistic Models
Figure 2 for Constraining the Dynamics of Deep Probabilistic Models
Figure 3 for Constraining the Dynamics of Deep Probabilistic Models
Figure 4 for Constraining the Dynamics of Deep Probabilistic Models
* 13 pages 
  Access Paper or Ask Questions

Dirichlet-based Gaussian Processes for Large-scale Calibrated Classification


May 28, 2018
Dimitrios Milios, Raffaello Camoriano, Pietro Michiardi, Lorenzo Rosasco, Maurizio Filippone

Figure 1 for Dirichlet-based Gaussian Processes for Large-scale Calibrated Classification
Figure 2 for Dirichlet-based Gaussian Processes for Large-scale Calibrated Classification
Figure 3 for Dirichlet-based Gaussian Processes for Large-scale Calibrated Classification
Figure 4 for Dirichlet-based Gaussian Processes for Large-scale Calibrated Classification

  Access Paper or Ask Questions

Calibrating Deep Convolutional Gaussian Processes


May 26, 2018
Gia-Lac Tran, Edwin V. Bonilla, John P. Cunningham, Pietro Michiardi, Maurizio Filippone

Figure 1 for Calibrating Deep Convolutional Gaussian Processes
Figure 2 for Calibrating Deep Convolutional Gaussian Processes
Figure 3 for Calibrating Deep Convolutional Gaussian Processes
Figure 4 for Calibrating Deep Convolutional Gaussian Processes
* 12 pages 
  Access Paper or Ask Questions

Pseudo-extended Markov chain Monte Carlo


Aug 17, 2017
Christopher Nemeth, Fredrik Lindsten, Maurizio Filippone, James Hensman

Figure 1 for Pseudo-extended Markov chain Monte Carlo
Figure 2 for Pseudo-extended Markov chain Monte Carlo
Figure 3 for Pseudo-extended Markov chain Monte Carlo
Figure 4 for Pseudo-extended Markov chain Monte Carlo

  Access Paper or Ask Questions

Entropic Trace Estimates for Log Determinants


Apr 24, 2017
Jack Fitzsimons, Diego Granziol, Kurt Cutajar, Michael Osborne, Maurizio Filippone, Stephen Roberts

Figure 1 for Entropic Trace Estimates for Log Determinants
Figure 2 for Entropic Trace Estimates for Log Determinants
Figure 3 for Entropic Trace Estimates for Log Determinants
Figure 4 for Entropic Trace Estimates for Log Determinants
* 16 pages, 4 figures, 2 tables, 2 algorithms 
  Access Paper or Ask Questions

Bayesian Inference of Log Determinants


Apr 05, 2017
Jack Fitzsimons, Kurt Cutajar, Michael Osborne, Stephen Roberts, Maurizio Filippone

Figure 1 for Bayesian Inference of Log Determinants
Figure 2 for Bayesian Inference of Log Determinants
Figure 3 for Bayesian Inference of Log Determinants
Figure 4 for Bayesian Inference of Log Determinants
* 12 pages, 3 figures 
  Access Paper or Ask Questions

AutoGP: Exploring the Capabilities and Limitations of Gaussian Process Models


Mar 06, 2017
Karl Krauth, Edwin V. Bonilla, Kurt Cutajar, Maurizio Filippone

Figure 1 for AutoGP: Exploring the Capabilities and Limitations of Gaussian Process Models
Figure 2 for AutoGP: Exploring the Capabilities and Limitations of Gaussian Process Models
* Edited results on RECTANGLES-IMAGE and related comments; minor additional edits 
  Access Paper or Ask Questions

Random Feature Expansions for Deep Gaussian Processes


Mar 01, 2017
Kurt Cutajar, Edwin V. Bonilla, Pietro Michiardi, Maurizio Filippone

Figure 1 for Random Feature Expansions for Deep Gaussian Processes
Figure 2 for Random Feature Expansions for Deep Gaussian Processes
Figure 3 for Random Feature Expansions for Deep Gaussian Processes
Figure 4 for Random Feature Expansions for Deep Gaussian Processes

  Access Paper or Ask Questions

Mini-Batch Spectral Clustering


Aug 12, 2016
Yufei Han, Maurizio Filippone

Figure 1 for Mini-Batch Spectral Clustering
Figure 2 for Mini-Batch Spectral Clustering
Figure 3 for Mini-Batch Spectral Clustering
Figure 4 for Mini-Batch Spectral Clustering

  Access Paper or Ask Questions

Preconditioning Kernel Matrices


May 25, 2016
Kurt Cutajar, Michael A. Osborne, John P. Cunningham, Maurizio Filippone

Figure 1 for Preconditioning Kernel Matrices
Figure 2 for Preconditioning Kernel Matrices

  Access Paper or Ask Questions

Enabling scalable stochastic gradient-based inference for Gaussian processes by employing the Unbiased LInear System SolvEr (ULISSE)


Sep 03, 2015
Maurizio Filippone, Raphael Engler

Figure 1 for Enabling scalable stochastic gradient-based inference for Gaussian processes by employing the Unbiased LInear System SolvEr (ULISSE)
Figure 2 for Enabling scalable stochastic gradient-based inference for Gaussian processes by employing the Unbiased LInear System SolvEr (ULISSE)
Figure 3 for Enabling scalable stochastic gradient-based inference for Gaussian processes by employing the Unbiased LInear System SolvEr (ULISSE)
Figure 4 for Enabling scalable stochastic gradient-based inference for Gaussian processes by employing the Unbiased LInear System SolvEr (ULISSE)
* 10 pages - paper accepted at ICML 2015 
  Access Paper or Ask Questions

MCMC for Variationally Sparse Gaussian Processes


Jun 12, 2015
James Hensman, Alexander G. de G. Matthews, Maurizio Filippone, Zoubin Ghahramani

Figure 1 for MCMC for Variationally Sparse Gaussian Processes
Figure 2 for MCMC for Variationally Sparse Gaussian Processes
Figure 3 for MCMC for Variationally Sparse Gaussian Processes
Figure 4 for MCMC for Variationally Sparse Gaussian Processes
* 16 pages 
  Access Paper or Ask Questions