Papers

A curated collection of papers he has found valuable, many of which have directly informed his research.

2021

• Causal Inference in AI Education: A Primer Journal of Causal Inference
• Explainable neural networks that simulate reasoning Nature

2020

• Challenges in Deploying Machine Learning: a Survey of Case Studies NeurIPS 2020
• The carbon impact of artificial intelligence Nature Machine Intelligence
• Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence Philosophy and Technology, Springer
• AI for social good: unlocking the opportunity for positive impact Nature Communications
• A Survey of Deep Learning for Scientific Discovery arXiv
• The Case for Bayesian Deep Learning arXiv
• Lagrangian Neural Networks arXiv
• Four Steps Towards Robust Artificial Intelligence arXiv

2019

• A deep learning framework for neuroscience Nature Neuroscience
• Posterior inference unchained with EL₂O arXiv
• Monte Carlo Gradient Estimation in Machine Learning arXiv
• Tackling Climate Change with Machine Learning arXiv
• Reconciling modern machine-learning practice and the classical bias–variance trade-off PNAS

2018

• Generalized massive optimal data compression MNRAS
• Massive optimal data compression and density estimation for scalable, likelihood-free inference in cosmology MNRAS
• Solving linear equations with messenger-field and conjugate gradient techniques A&A

2017

• Wiener filter reloaded: fast signal reconstruction without preconditioning MNRAS
• Why Does Deep and Cheap Learning Work So Well? Springer Nature

2015

• Probabilistic machine learning and artificial intelligence Nature
• Deep learning Nature
• Taking the Human Out of the Loop: A Review of Bayesian Optimization IEEE

2013

• Bayesian non-parametrics and the probabilistic approach to modelling The Royal Society Publishing
• Efficient sampling of fast and slow cosmological parameters Physical Review

2012

• Representation Learning: A Review and New Perspectives arXiv

2011

• Additive Gaussian Processes arXiv
• Distributed Gaussian Processes ICML
• Intelligent design: on the emulation of cosmological simulations IOP
• The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo JMLR

2010

• A Tutorial on Bayesian Optimization arXiv

Before 2010

• Fast optimal CMB power spectrum estimation with Hamiltonian sampling MNRAS · 2008
• Bayes in the sky: Bayesian inference and model selection in cosmology Contemporary Physics · 2008
• Fast cosmological parameter estimation using neural networks MNRAS · 2007
• Pico: Parameters for the Impatient Cosmologist IOP · 2007
• Random Features for Large-Scale Kernel Machines NIPS · 2007
• Efficient Cosmological Parameter Estimation with Hamiltonian Monte Carlo APS · 2007
• Sparse Gaussian Processes using Pseudo-inputs NIPS · 2005
• A Bayesian Committee Machine Neural Computation · 2000
• Massive Lossless Data Compression and Multiple Parameter Estimation from Galaxy Spectra MNRAS · 2000
• Karhunen-Loève Eigenvalue Problems in Cosmology: How Should We Tackle Large Data Sets? IOP · 1997
• No free lunch theorems for optimization IEEE · 1997

Classical Papers

• A Bayesian approach to model inadequacy for polynomial regression Biometrika · 1975