| Scalable Variational Gaussian Process Classification. J Hensman, A Matthews, Z Ghahramani The 18th International Conference on Artificial Intelligence and Statistics …, 2015 | 798 | 2015 |
| GPflow: A Gaussian process library using TensorFlow AGG Matthews, M van der Wilk, T Nickson, K Fujii, A Boukouvalas, ... Journal of Machine Learning Research 18 (40), 1-6, 2017 | 759* | 2017 |
| Ab-Initio Solution of the Many-Electron Schr\" odinger Equation with Deep Neural Networks D Pfau, JS Spencer, AGG Matthews, WMC Foulkes arXiv preprint arXiv:1909.02487, 2019 | 620 | 2019 |
| Gaussian Process Behaviour in Wide Deep Neural Networks AGG Matthews, J Hron, M Rowland, RE Turner, Z Ghahramani International Conference on Learning Representations (ICLR), 2018 | 613* | 2018 |
| Pushing the frontiers of density functionals by solving the fractional electron problem J Kirkpatrick, B McMorrow, DHP Turban, AL Gaunt, JS Spencer, ... Science 374 (6573), 1385-1389, 2021 | 345 | 2021 |
| On Sparse Variational Methods and the Kullback-Leibler Divergence between Stochastic Processes AGG Matthews, J Hensman, RE Turner, Z Ghahramani The 19th International Conference on Artificial Intelligence and Statistics …, 2016 | 219* | 2016 |
| Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks J Bradshaw, AGG Matthews, Z Ghahramani arXiv preprint arXiv:1707.02476, 2017 | 204 | 2017 |
| Functional Regularisation for Continual Learning with Gaussian Processes MK Titsias, J Schwarz, AGG Matthews, R Pascanu, YW Teh International Conference on Learning Representations, 2019 | 191 | 2019 |
| MCMC for variationally sparse Gaussian processes J Hensman, AG Matthews, M Filippone, Z Ghahramani Advances in Neural Information Processing Systems, 1648-1656, 2015 | 178 | 2015 |
| Measurement and simulation of the effect of compaction on the pore structure and saturated hydraulic conductivity of grassland and arable soil GP Matthews, GM Laudone, AS Gregory, NRA Bird, AG de G Matthews, ... Water Resources Research 46 (5), 2010 | 85* | 2010 |
| Variational Bayesian dropout: pitfalls and fixes J Hron, A Matthews, Z Ghahramani Proceedings of Machine Learning Research, 2018 | 84 | 2018 |
| Scalable Gaussian process inference using variational methods AGG Matthews University of Cambridge, 2017 | 78 | 2017 |
| Annealed flow transport monte carlo M Arbel, A Matthews, A Doucet International Conference on Machine Learning, 318-330, 2021 | 69 | 2021 |
| Variational Gaussian Dropout is not Bayesian J Hron, AGG Matthews, Z Ghahramani arXiv preprint arXiv:1711.02989, 2017 | 62 | 2017 |
| Score-based diffusion meets annealed importance sampling A Doucet, W Grathwohl, AG Matthews, H Strathmann Advances in Neural Information Processing Systems 35, 21482-21494, 2022 | 42* | 2022 |
| Continual Repeated Annealed Flow transport Monte Carlo A Matthews, M Arbel, DJ Rezende, A Doucet International Conference on Machine Learning, 15196-15219, 2022 | 40 | 2022 |
| Sample-then-optimize posterior sampling for bayesian linear models AGG Matthews, J Hron, RE Turner, Z Ghahramani NeurIPS Workshop on Advances in Approximate Bayesian Inference, 2017 | 31 | 2017 |
| Aspects of scaling and scalability for flow-based sampling of lattice QCD R Abbott, MS Albergo, A Botev, D Boyda, K Cranmer, DC Hackett, ... The European Physical Journal A 59 (11), 257, 2023 | 27 | 2023 |
| Sampling QCD field configurations with gauge-equivariant flow models R Abbott, MS Albergo, A Botev, D Boyda, K Cranmer, DC Hackett, ... arXiv preprint arXiv:2208.03832, 2022 | 21 | 2022 |
| Normalizing flows for lattice gauge theory in arbitrary space-time dimension R Abbott, MS Albergo, A Botev, D Boyda, K Cranmer, DC Hackett, ... arXiv preprint arXiv:2305.02402, 2023 | 19 | 2023 |
Zoubin GhahramaniProfessor, University of Cambridge, and Distinguished Researcher, GoogleVerified email at eng.cam.ac.uk