Mark van der Wilk

Affiliations

Imperial College London

papers

421

total citations

papers (14)

Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty

NEURIPS 2020arXiv

129

citations

Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations

NEURIPS 2022arXiv

citations

Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning

NEURIPS 2025arXiv

citations

Learning in Deep Factor Graphs with Gaussian Belief Propagation

ICML 2024arXiv

citations

Mark van der Wilk

Affiliations

papers (14)

Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty

Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations

Relaxing Equivariance Constraints with Non-stationary Continuous Filters

Speedy Performance Estimation for Neural Architecture Search

Deep Neural Networks as Point Estimates for Deep Gaussian Processes

A Bayesian Perspective on Training Speed and Model Selection

SnAKe: Bayesian Optimization with Pathwise Exploration

Learning Layer-wise Equivariances Automatically using Gradients

Rethinking Aleatoric and Epistemic Uncertainty

A Meta-Learning Approach to Bayesian Causal Discovery

Memory safe computations with XLA compiler

Bivariate Causal Discovery using Bayesian Model Selection

Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning

Learning in Deep Factor Graphs with Gaussian Belief Propagation

papers (14)

Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty

Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations

Relaxing Equivariance Constraints with Non-stationary Continuous Filters

Speedy Performance Estimation for Neural Architecture Search

Deep Neural Networks as Point Estimates for Deep Gaussian Processes

A Bayesian Perspective on Training Speed and Model Selection

SnAKe: Bayesian Optimization with Pathwise Exploration

Learning Layer-wise Equivariances Automatically using Gradients

Rethinking Aleatoric and Epistemic Uncertainty

A Meta-Learning Approach to Bayesian Causal Discovery

Memory safe computations with XLA compiler

Bivariate Causal Discovery using Bayesian Model Selection

Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning

Learning in Deep Factor Graphs with Gaussian Belief Propagation