Below is a collection of interesting papers. Some of them have been very useful and are relevant to my research.

2021

  1. Causal Inference in AI Education: A Primer (Journal of Causal Inference, )
  2. Explainable neural networks that simulate reasoning (Nature, )

2020

  1. Challenges in Deploying Machine Learning: a Survey of Case Studies (NeurIPS 2020, )
  2. The carbon impact of artifcial intelligence (Nature Machine Intelligence, )
  3. Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence (Philosophy and Technology, Springer, )
  4. AI for social good: unlocking the opportunity for positive impact (Nature Communications, )
  5. A Survey of Deep Learning for Scientific Discovery (arXiv, )
  6. The Case for Bayesian Deep Learning (arXiv, )
  7. Lagrangian Neural Networks (arXiv, )
  8. Four Steps Towards Robust Artificial Intelligence (arXiv, )

2019

  1. A deep learning framework for neuroscience (Nature Neuroscience, )
  2. Posterior inference unchained with EL2O (arXiv, )
  3. Monte Carlo Gradient Estimation in Machine Learning (arXiv, )
  4. Tackling Climate Change with Machine Learning (arXiv, )
  5. Reconciling modern machine-learning practice and the classical bias–variance trade-off (PNAS, )

2018

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

2017

  1. Wiener filter reloaded: fast signal reconstruction without preconditioning (MNRAS, )
  2. Why Does Deep and Cheap Learning Work So Well? (Springer Nature, )

2015

  1. Probabilistic machine learning and artificial intelligence (Nature, )
  2. Deep learning (Nature, )
  3. Taking the Human Out of the Loop: A Review of Bayesian Optimization (IEEE, )

2013

  1. Bayesian non-parametrics and the probabilistic approach to modelling (The Royal Society Publishing, )
  2. Efficient sampling of fast and slow cosmological parameters (Physical Review, )

2012

  1. Representation Learning: A Review and New Perspectives (arXiv, )

2011

  1. Additive Gaussian Processes (arXiv, )
  2. Distributed Gaussian Processes (ICML, )
  3. Intelligent design: on the emulation of cosmological simulations (IOP, )
  4. The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo (JMLR, )

2010

  1. A Tutorial on Bayesian Optimization (arXiv, )

Before 2010

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

Classical Papers

  1. A Bayesian approach to model inadequacy for polynomial regression (Biometrika, 1975, )