Mark van der Wilk

发表

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

Carl E. Rasmussen, Alessandro Davide Ialongo, Mark van der Wilk, 2018, ArXiv.

Distributed Variational Inference in Sparse Gaussian Process Regression and Latent Variable Models

Carl E. Rasmussen, Mark van der Wilk, Yarin Gal, 2014, NIPS.

Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning

Roberto Cipolla, Mark van der Wilk, Adrian Weller, 2017, IJCAI.

Convolutional Gaussian Processes

Carl E. Rasmussen, James Hensman, Mark van der Wilk, 2017, NIPS.

Understanding Variational Inference in Function-Space pdf

Mark van der Wilk, Sebastian W. Ober, David R. Burt, 2020, ArXiv.

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

Mark van der Wilk, Yarin Gal, Clare Lyle, 2020, ArXiv.

Bayesian Layers: A Module for Neural Network Uncertainty

Dustin Tran, Michael W. Dusenberry, Mark van der Wilk, 2018, NeurIPS.

Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty pdf

Konstantinos Kamnitsas, Mark van der Wilk, Nick Pawlowski, 2020, NeurIPS.

On the Benefits of Invariance in Neural Networks pdf

Mark van der Wilk, Yarin Gal, Clare Lyle, 2020, ArXiv.

Non-Factorised Variational Inference in Dynamical Systems pdf

Carl E. Rasmussen, James Hensman, Alessandro Davide Ialongo, 2018, ArXiv.

Learning Invariances using the Marginal Likelihood

James Hensman, Mark van der Wilk, Matthias Bauer, 2018, NeurIPS.

Variational Gaussian Process Models without Matrix Inverses

Mark van der Wilk, 2019, AABI.

GPflow: A Gaussian Process Library using TensorFlow

Alexis Boukouvalas, James Hensman, Zoubin Ghahramani, 2016, J. Mach. Learn. Res..

Mark van der Wilk, Adria Garriga-Alonso, Adrià Garriga-Alonso, 2021, UAI.

Design of Experiments for Verifying Biomolecular Networks pdf

Mark van der Wilk, Ruth Misener, John Goertz, 2020, ArXiv.

Sparse Gaussian process approximations and applications

Mark van der Wilk, 2019 .

A Bayesian Perspective on Training Speed and Model Selection pdf

Mark van der Wilk, Yarin Gal, Clare Lyle, 2020, NeurIPS.

Capsule Networks - A Probabilistic Perspective pdf

Mark van der Wilk, Yarin Gal, Lewis Smith, 2020, ArXiv.

Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning

Roberto Cipolla, Mark van der Wilk, Adrian Weller, 2017, IJCAI 2017.

Convergence of Sparse Variational Inference in Gaussian Processes Regression

Mark van der Wilk, Carl Edward Rasmussen, David R. Burt, 2020, J. Mach. Learn. Res..

Rates of Convergence for Sparse Variational Gaussian Process Regression

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

Translation Insensitivity for Deep Convolutional Gaussian Processes

James Hensman, Mark van der Wilk, Artem Artemev, 2019, ArXiv.

Understanding Probabilistic Sparse Gaussian Process Approximations

Carl E. Rasmussen, Mark van der Wilk, Matthias Bauer, 2016, NIPS.

Overcoming Mean-Field Approximations in Recurrent Gaussian Process Models

Carl E. Rasmussen, James Hensman, Alessandro Davide Ialongo, 2019, ICML.

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

Mark van der Wilk, Creighton Heaukulani, Creighton Heaukulani, 2019, NeurIPS.

Variational Orthogonal Features pdf

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

Variational Inference in Sparse Gaussian Process Regression and Latent Variable Models - a Gentle Tutorial

Mark van der Wilk, Yarin Gal, 2014 .

Barely Biased Learning for Gaussian Process Regression pdf

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

Last Layer Marginal Likelihood for Invariance Learning pdf

Mark van der Wilk, Sebastian W. Ober, Pola Elisabeth Schwobel, 2021, ArXiv.

Bayesian Neural Network Priors Revisited pdf

Mark van der Wilk, Florian Wenzel, Richard Turner, 2021, ArXiv.

Deep Neural Networks as Point Estimates for Deep Gaussian Processes pdf

James Hensman, Mark van der Wilk, Carl Henrik Ek, 2021, NeurIPS.

The Promises and Pitfalls of Deep Kernel Learning

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

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

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

GPflux: A Library for Deep Gaussian Processes pdf

James Hensman, Mark van der Wilk, Felix Leibfried, 2021, ArXiv.

A Bayesian Approach to Invariant Deep Neural Networks pdf

Mark van der Wilk, Marco Federici, Vincent Fortuin, 2021, ArXiv.

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

Mark van der Wilk, Laurence Aitchison, Vincent Fortuin, 2021, Softw. Impacts.

Data augmentation in Bayesian neural networks and the cold posterior effect pdf

Seth Nabarro, Mark van der Wilk, Laurence Aitchison, 2021, UAI.

Disentangling Sources of Uncertainty for Active Exploration

Mark van der Wilk, D. Lines, 2019 .

Variational Inference for Latent Variable Modelling of Correlation Structure

Mark van der Wilk, 2014 .

Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty pdf

Konstantinos Kamnitsas, Mark van der Wilk, Nick Pawlowski, 2020, NeurIPS.

A Framework for Interdomain and Multioutput Gaussian Processes pdf

James Hensman, Mark van der Wilk, Vincent Adam, 2020, ArXiv.

Memory Safe Computations with XLA Compiler

Mark van der Wilk, A. Artemev, Tilman Roeder, 2022, NeurIPS.

Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations

Mark van der Wilk, Tycho F. A. van der Ouderaa, Alexander Immer, 2022, ArXiv.

Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations

Mark van der Wilk, Tycho F. A. van der Ouderaa, Alexander Immer, 2022, NeurIPS.

Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees

Mark van der Wilk, David R. Burt, C. Rasmussen, 2022, ArXiv.

Concrete Problems for Safety in Autonomous Vehicles through Bayesian Deep Learning

Mark van der Wilk, Rowan McAllister, Y. Gal, 2017 .

SnAKe: Bayesian Optimization with Pathwise Exploration

Mark van der Wilk, Robert M. Lee, R. Misener, 2022, ArXiv.

Combining Multi-Fidelity Modelling and Asynchronous Batch Bayesian Optimization

Mark van der Wilk, Robert M. Lee, R. Misener, 2022, ArXiv.

Variational Inference in Sparse Gaussian Process Regression and Latent Variable Models - a Gentle Tutorial

Mark van der Wilk, Y. Gal, 2014, 1402.1412.

SnAKe: Bayesian Optimization with Pathwise Exploration

Mark van der Wilk, Robert M. Lee, R. Misener, 2022, 2202.00060.

Bayesian Neural Network Priors Revisited

Richard E. Turner, Mark van der Wilk, Gunnar Rätsch, 2021, ICLR.

GPflux: A Library for Deep Gaussian Processes

Mark van der Wilk, S. T. John, M. Deisenroth, 2021, ArXiv.

Combining Multi-Fidelity Modelling and Asynchronous Batch Bayesian Optimization

Mark van der Wilk, Robert M. Lee, R. Misener, 2022, Comput. Chem. Eng..

Speedy Performance Estimation for Neural Architecture Search

Mark van der Wilk, Clare Lyle, Y. Gal, 2020, NeurIPS.

Last Layer Marginal Likelihood for Invariance Learning

Mark van der Wilk, Sebastian W. Ober, Martin Jørgensen, 2021, AISTATS.

Learning Invariant Weights in Neural Networks

Mark van der Wilk, Tycho F. A. van der Ouderaa, 2022, UAI.

Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels

Mark van der Wilk, Tycho F. A. van der Ouderaa, B. Schölkopf, 2023, ICML.

Bayesian Image Classification with Deep Convolutional Gaussian Processes

Mark van der Wilk, J. Hensman, Vincent Dutordoir, 2019, AISTATS.

Relaxing Equivariance Constraints with Non-stationary Continuous Filters

Mark van der Wilk, Tycho F. A. van der Ouderaa, David W. Romero, 2022, NeurIPS.

Current Methods for Drug Property Prediction in the Real World

Mark van der Wilk, A. Dimitracopoulos, Ryan D. Greenhalgh, 2023, ArXiv.

The Promises and Pitfalls of Deep Kernel Learning

Mark van der Wilk, Sebastian W. Ober, C. Rasmussen, 2021, UAI.

Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code

Mark van der Wilk, Shahin Honarvar, Alastair Donaldson, 2023, ArXiv.

Actually Sparse Variational Gaussian Processes

Mark van der Wilk, Daniel Augusto R. M. A. de Souza, M. Deisenroth, 2023, AISTATS.

Practical Path-based Bayesian Optimization

Mark van der Wilk, Robert M. Lee, B. Shafei, 2023, ArXiv.

SnAKe: Bayesian Optimization with Pathwise Exploration

Mark van der Wilk, Robert M. Lee, R. Misener, 2022, NeurIPS.

Recommendations for Baselines and Benchmarking Approximate Gaussian Processes

Mark van der Wilk, Sebastian W. Ober, A. Artemev, 2024, 2402.09849.

Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees

Mark van der Wilk, David R. Burt, C. Rasmussen, 2022, ArXiv.

Causal Discovery using Bayesian Model Selection

Mark van der Wilk, Anish Dhir, 2023, ArXiv.

Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations

Mark van der Wilk, Tycho F. A. van der Ouderaa, Alexander Immer, 2022, NeurIPS.

Appendix of Speedy Performance Estimation for Neural Architecture Search

Mark van der Wilk, Clare Lyle, Y. Gal, 2021 .

Learning in Deep Factor Graphs with Gaussian Belief Propagation

Mark van der Wilk, Seth Nabarro, Andrew J Davison, 2023, ICML.