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 Mark van der Wilk

A Bayesian Approach to Invariant Deep Neural Networks


Jul 20, 2021
Nikolaos Mourdoukoutas, Marco Federici, Georges Pantalos, Mark van der Wilk, Vincent Fortuin

* 8 pages, 3 figures, To be published in ICML UDL 2021 

  Access Paper or Ask Questions

Last Layer Marginal Likelihood for Invariance Learning


Jun 14, 2021
Pola Elisabeth Schwöbel, Martin Jørgensen, Sebastian W. Ober, Mark van der Wilk


  Access Paper or Ask Questions

Data augmentation in Bayesian neural networks and the cold posterior effect


Jun 10, 2021
Seth Nabarro, Stoil Ganev, Adrià Garriga-Alonso, Vincent Fortuin, Mark van der Wilk, Laurence Aitchison


  Access Paper or Ask Questions

BNNpriors: A library for Bayesian neural network inference with different prior distributions


May 14, 2021
Vincent Fortuin, Adrià Garriga-Alonso, Mark van der Wilk, Laurence Aitchison

* Accepted for publication at Software Impacts 

  Access Paper or Ask Questions

Deep Neural Networks as Point Estimates for Deep Gaussian Processes


May 10, 2021
Vincent Dutordoir, James Hensman, Mark van der Wilk, Carl Henrik Ek, Zoubin Ghahramani, Nicolas Durrande


  Access Paper or Ask Questions

GPflux: A Library for Deep Gaussian Processes


Apr 12, 2021
Vincent Dutordoir, Hugh Salimbeni, Eric Hambro, John McLeod, Felix Leibfried, Artem Artemev, Mark van der Wilk, James Hensman, Marc P. Deisenroth, ST John


  Access Paper or Ask Questions

The Promises and Pitfalls of Deep Kernel Learning


Feb 24, 2021
Sebastian W. Ober, Carl E. Rasmussen, Mark van der Wilk

* 18 pages 

  Access Paper or Ask Questions

Tighter Bounds on the Log Marginal Likelihood of Gaussian Process Regression Using Conjugate Gradients


Feb 16, 2021
Artem Artemev, David R. Burt, Mark van der Wilk

* Preprint 

  Access Paper or Ask Questions

Bayesian Neural Network Priors Revisited


Feb 12, 2021
Vincent Fortuin, Adrià Garriga-Alonso, Florian Wenzel, Gunnar Rätsch, Richard Turner, Mark van der Wilk, Laurence Aitchison


  Access Paper or Ask Questions

Correlated Weights in Infinite Limits of Deep Convolutional Neural Networks


Jan 11, 2021
Adrià Garriga-Alonso, Mark van der Wilk

* Presented at 3rd Symposium on Advances in Approximate Bayesian Inference 

  Access Paper or Ask Questions

Design of Experiments for Verifying Biomolecular Networks


Nov 25, 2020
Ruby Sedgwick, John Goertz, Molly Stevens, Ruth Misener, Mark van der Wilk

* Comment: Updated to correct typo "that that" => "that" 

  Access Paper or Ask Questions

Understanding Variational Inference in Function-Space


Nov 18, 2020
David R. Burt, Sebastian W. Ober, Adrià Garriga-Alonso, Mark van der Wilk

* 19 pages 

  Access Paper or Ask Questions

A Bayesian Perspective on Training Speed and Model Selection


Oct 27, 2020
Clare Lyle, Lisa Schut, Binxin Ru, Yarin Gal, Mark van der Wilk

* To be presented at NeurIPS 2020 

  Access Paper or Ask Questions

Convergence of Sparse Variational Inference in Gaussian Processes Regression


Aug 01, 2020
David R. Burt, Carl Edward Rasmussen, Mark van der Wilk

* Journal of Machine Learning Research, 21(131), 1-63 (2020) 
* Extended version of http://proceedings.mlr.press/v97/burt19a.html (arxiv version: arXiv:1903.03571 ). Published in Journal of Machine Learning Research: http://jmlr.org/papers/v21/19-1015.html. Code available at: https://github.com/markvdw/RobustGP 

  Access Paper or Ask Questions

Variational Orthogonal Features


Jun 23, 2020
David R. Burt, Carl Edward Rasmussen, Mark van der Wilk


  Access Paper or Ask Questions

Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty


Jun 10, 2020
Miguel Monteiro, Loïc Le Folgoc, Daniel Coelho de Castro, Nick Pawlowski, Bernardo Marques, Konstantinos Kamnitsas, Mark van der Wilk, Ben Glocker

* 17 pages, 11 figures, 2 tables 

  Access Paper or Ask Questions

Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search


Jun 08, 2020
Binxin Ru, Clare Lyle, Lisa Schut, Mark van der Wilk, Yarin Gal

* 14 pages, 10 figures 

  Access Paper or Ask Questions

On the Benefits of Invariance in Neural Networks


May 01, 2020
Clare Lyle, Mark van der Wilk, Marta Kwiatkowska, Yarin Gal, Benjamin Bloem-Reddy


  Access Paper or Ask Questions

Capsule Networks -- A Probabilistic Perspective


Apr 07, 2020
Lewis Smith, Lisa Schut, Yarin Gal, Mark van der Wilk


  Access Paper or Ask Questions

A Framework for Interdomain and Multioutput Gaussian Processes


Mar 02, 2020
Mark van der Wilk, Vincent Dutordoir, ST John, Artem Artemev, Vincent Adam, James Hensman


  Access Paper or Ask Questions

Scalable Bayesian dynamic covariance modeling with variational Wishart and inverse Wishart processes


Jun 22, 2019
Creighton Heaukulani, Mark van der Wilk


  Access Paper or Ask Questions

Overcoming Mean-Field Approximations in Recurrent Gaussian Process Models


Jun 13, 2019
Alessandro Davide Ialongo, Mark van der Wilk, James Hensman, Carl Edward Rasmussen

* PMLR 97:2931-2940 (2019) 
* 10 pages, 4 figures, 3 tables. Published in the proceedings of the Thirty-sixth International Conference on Machine Learning (ICML), 2019 

  Access Paper or Ask Questions

Rates of Convergence for Sparse Variational Gaussian Process Regression


Mar 08, 2019
David R. Burt, Carl E. Rasmussen, Mark van der Wilk


  Access Paper or Ask Questions

Translation Insensitivity for Deep Convolutional Gaussian Processes


Feb 15, 2019
Vincent Dutordoir, Mark van der Wilk, Artem Artemev, Marcin Tomczak, James Hensman


  Access Paper or Ask Questions

Non-Factorised Variational Inference in Dynamical Systems


Dec 14, 2018
Alessandro Davide Ialongo, Mark van der Wilk, James Hensman, Carl Edward Rasmussen

* 6 pages, 1 figure, 1 table 

  Access Paper or Ask Questions

Bayesian Layers: A Module for Neural Network Uncertainty


Dec 11, 2018
Dustin Tran, Michael W. Dusenberry, Mark van der Wilk, Danijar Hafner

* Presented in NeurIPS 2018 workshop Bayesian Deep Learning. Code available at https://github.com/tensorflow/tensor2tensor 

  Access Paper or Ask Questions

Closed-form Inference and Prediction in Gaussian Process State-Space Models


Dec 10, 2018
Alessandro Davide Ialongo, Mark van der Wilk, Carl Edward Rasmussen

* 7 pages, 6 figures 

  Access Paper or Ask Questions

Learning Invariances using the Marginal Likelihood


Aug 16, 2018
Mark van der Wilk, Matthias Bauer, ST John, James Hensman


  Access Paper or Ask Questions

Convolutional Gaussian Processes


Sep 06, 2017
Mark van der Wilk, Carl Edward Rasmussen, James Hensman

* To appear in Advances in Neural Information Processing Systems 30 (NIPS 2017) 

  Access Paper or Ask Questions