| The malicious use of artificial intelligence: Forecasting, prevention, and mitigation M Brundage, S Avin, J Clark, H Toner, P Eckersley, B Garfinkel, A Dafoe, ... arXiv preprint arXiv:1802.07228, 2018 | 617 | 2018 |
| Towards Robust Evaluations of Continual Learning S Farquhar, Y Gal arXiv preprint arXiv:1805.09733, 2018 | 190 | 2018 |
| Benchmarking Bayesian Deep Learning with Diabetic Retinopathy Diagnosis A Filos, S Farquhar, AN Gomez, TGJ Rudner, Z Kenton, L Smith, ... Preprint, 2019 | 71* | 2019 |
| A Unifying Bayesian View of Continual Learning S Farquhar, Y Gal Bayesian Deep Learning Workshop at NeurIPS arXiv:1902.06494, 2018 | 46 | 2018 |
| Global Catastrophic Risks O Cotton-Barratt, S Farquhar, J Halstead, S Schubert, A Snyder-Beattie Global Challenges Foundation, 2016 | 45* | 2016 |
| Radial Bayesian Neural Networks: Robust Variational Inference In Big Models S Farquhar, M Osborne, Y Gal Proceedings of the International Conference on Artificial Intelligence and …, 2020 | 44* | 2020 |
| Existential Risk: Diplomacy and Governance S Farquhar, J Halstead, O Cotton-Barratt, S Schubert, H Belfield, ... Global Priorities Project, 2017 | 29* | 2017 |
| On Statistical Bias In Active Learning: How and When To Fix It S Farquhar, Y Gal, T Rainforth International Conference on Learning Representations, 2021 | 24 | 2021 |
| Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations S Farquhar, L Smith, Y Gal Advances in Neural Information Processing Systems, 2020 | 23 | 2020 |
| Uncertainty Baselines: Benchmarks for uncertainty & robustness in deep learning Z Nado, N Band, M Collier, J Djolonga, MW Dusenberry, S Farquhar, ... arXiv preprint arXiv:2106.04015, 2021 | 22 | 2021 |
| Pricing externalities to balance public risks and benefits of research S Farquhar, O Cotton-Barratt, A Snyder-Beattie Health security 15 (4), 401-408, 2017 | 11* | 2017 |
| Single Shot Structured Pruning Before Training J van Amersfoort, M Alizadeh, S Farquhar, N Lane, Y Gal arXiv preprint arXiv:2007.00389, 2020 | 10 | 2020 |
| Try Depth Instead of Weight Correlations: Mean-field is a Less Restrictive Assumption for Variational Inference in Deep Networks S Farquhar, L Smith, Y Gal Bayesian Deep Learning Workshop at NeurIPS, 2019 | 7* | 2019 |
| Differentially Private Continual Learning S Farquhar, Y Gal Privacy in Machine Learning and AI workshop at the International Conference …, 2018 | 7 | 2018 |
| Active Testing: Sample-Efficient Model Evaluation J Kossen, S Farquhar, Y Gal, T Rainforth International Conference on Machine Learning, 2021 | 6 | 2021 |
| A Simple Baseline for Batch Active Learning with Stochastic Acquisition Functions A Kirsch, S Farquhar, Y Gal arXiv preprint arXiv:2106.12059, 2021 | 4 | 2021 |
| Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients M Alizadeh, SA Tailor, LM Zintgraf, J van Amersfoort, S Farquhar, ... International Conference on Learning Representations, 2022 | 3 | 2022 |
| Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt S Mindermann, JM Brauner, MT Razzak, M Sharma, A Kirsch, W Xu, ... International Conference on Machine Learning, 15630-15649, 2022 | 1 | 2022 |
| Path-Specific Objectives for Safer Agent Incentives S Farquhar, R Carey, T Everitt AAAI, 2022 | 1 | 2022 |
| Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation J Kossen, S Farquhar, Y Gal, T Rainforth arXiv preprint arXiv:2202.06881, 2022 | | 2022 |
Yarin GalAssociate Professor, University of OxfordVerified email at cs.ox.ac.uk
