| Batchbald: Efficient and diverse batch acquisition for deep bayesian active learning A Kirsch, J van Amersfoort, Y Gal Advances in Neural Information Processing Systems (NeurIPS), 7024-7035, 2019 | 480 | 2019 |
| Deep Deterministic Uncertainty: A New Simple Baseline J Mukhoti, A Kirsch, J van Amersfoort, PHS Torr, Y Gal Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 116* | 2023 |
| Plex: towards reliability using pretrained large model extensions (2022) D Tran, J Liu, MW Dusenberry, D Phan, M Collier, J Ren, K Han, Z Wang, ... URL https://arxiv. org/abs/2207.07411, 0 | 66* | |
| 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 (ICML), 15630-15649, 2022 | 48 | 2022 |
| Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning A Kirsch, S Farquhar, P Atighehchian, A Jesson, F Branchaud-Charron, ... Transactions on Machine Learning Research (TMLR), 0 | 21* | |
| Causal-bald: Deep bayesian active learning of outcomes to infer treatment-effects from observational data A Jesson, P Tigas, J van Amersfoort, A Kirsch, U Shalit, Y Gal Advances in Neural Information Processing Systems (NeurIPS) 34, 30465-30478, 2021 | 17 | 2021 |
| Unpacking information bottlenecks: Unifying information-theoretic objectives in deep learning A Kirsch, C Lyle, Y Gal Workshop Uncertainty & Robustness in Deep Learning at Int. Conf. on Machine …, 2020 | 16* | 2020 |
| A Note on "Assessing Generalization of SGD via Disagreement" A Kirsch, Y Gal Transactions on Machine Learning Research (TMLR), 2022 | 11 | 2022 |
| Test distribution-aware active learning: A principled approach against distribution shift and outliers A Kirsch, T Rainforth, Y Gal arXiv preprint arXiv:2106.11719, 2021 | 11* | 2021 |
| Prediction-Oriented Bayesian Active Learning FB Smith, A Kirsch, S Farquhar, Y Gal, A Foster, T Rainforth International Conference on Artificial Intelligence and Statistics (AISTATS …, 2023 | 7* | 2023 |
| A Practical & Unified Notation for Information-Theoretic Quantities in ML A Kirsch, Y Gal arXiv preprint arXiv:2106.12062, 2021 | 4 | 2021 |
| Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities A Kirsch, Y Gal Transactions on Machine Learning Research (TMLR), 2022 | 3 | 2022 |
| Black-Box Batch Active Learning for Regression A Kirsch Transactions on Machine Learning Research, 2023 | 2 | 2023 |
| PowerEvaluationBALD: Efficient Evaluation-Oriented Deep (Bayesian) Active Learning with Stochastic Acquisition Functions A Kirsch arXiv preprint arXiv:2101.03552, 2021 | 2 | 2021 |
| MDP environments for the OpenAI Gym A Kirsch arXiv preprint arXiv:1709.09069, 2017 | 2 | 2017 |
| Does Deep Learning on a Data Diet reproduce? Overall yes, but GraNd at Initialization does not A Kirsch Transactions on Machine Learning Research, 2023 | | 2023 |
| Speeding Up BatchBALD: A k-BALD Family of Approximations for Active Learning A Kirsch arXiv preprint arXiv:2301.09490, 2023 | | 2023 |
| Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling A Kirsch, J Kossen, Y Gal arXiv preprint arXiv:2205.08766, 2022 | | 2022 |
| Proseminar: Perlen der Informatik II Aussagenlogik–Korrektheit und Vollständigkeit des natürlichen Schließens A Kirsch | | 2008 |
Yarin GalAssociate Professor, University of OxfordVerified email at cs.ox.ac.uk
