| Asymmetric shapley values: incorporating causal knowledge into model-agnostic explainability C Frye, C Rowat, I Feige Advances in neural information processing systems 33, 1229-1239, 2020 | 222 | 2020 |
| JUNIPR: a framework for unsupervised machine learning in particle physics A Andreassen, I Feige, C Frye, MD Schwartz The European Physical Journal C 79 (2), 102, 2019 | 157 | 2019 |
| Shapley explainability on the data manifold C Frye, D de Mijolla, T Begley, L Cowton, M Stanley, I Feige International Conference on Learning Representations, 2021 | 143 | 2021 |
| Hard-soft-collinear factorization to all orders I Feige, MD Schwartz Physical Review D 90 (10), 105020, 2014 | 128 | 2014 |
| A complete basis of helicity operators for subleading factorization I Feige, DW Kolodrubetz, I Moult, IW Stewart Journal of High Energy Physics 2017 (11), 1-109, 2017 | 90 | 2017 |
| Precision jet substructure from boosted event shapes I Feige, MD Schwartz, IW Stewart, J Thaler Physical Review Letters 109 (9), 092001, 2012 | 90 | 2012 |
| Explainability for fair machine learning T Begley, T Schwedes, C Frye, I Feige arXiv preprint arXiv:2010.07389, 2020 | 53 | 2020 |
| An on-shell approach to factorization I Feige, MD Schwartz Physical Review D—Particles, Fields, Gravitation, and Cosmology 88 (6), 065021, 2013 | 43 | 2013 |
| binary junipr: An Interpretable Probabilistic Model for Discrimination A Andreassen, I Feige, C Frye, MD Schwartz Physical review letters 123 (18), 182001, 2019 | 28 | 2019 |
| Improving Gaussian mixture latent variable model convergence with Optimal Transport B Gaujac, I Feige, D Barber Asian Conference on Machine Learning, 737-752, 2021 | 14* | 2021 |
| Streamlining resummed QCD calculations using Monte Carlo integration D Farhi, I Feige, M Freytsis, MD Schwartz Journal of High Energy Physics 2016 (8), 1-34, 2016 | 12 | 2016 |
| Removing phase-space restrictions in factorized cross sections I Feige, MD Schwartz, K Yan Physical Review D 91 (9), 094027, 2015 | 12 | 2015 |
| Human-interpretable model explainability on high-dimensional data D de Mijolla, C Frye, M Kunesch, J Mansir, I Feige arXiv preprint arXiv:2010.07384, 2020 | 11 | 2020 |
| Invariant-equivariant representation learning for multi-class data I Feige International Conference on Machine Learning, 1882-1891, 2019 | 9 | 2019 |
| Learning disentangled representations with the wasserstein autoencoder B Gaujac, I Feige, D Barber Machine Learning and Knowledge Discovery in Databases. Research Track …, 2021 | 8 | 2021 |
| Parenting: Safe reinforcement learning from human input C Frye, I Feige arXiv preprint arXiv:1902.06766, 2019 | 8 | 2019 |
| Representation Learning for High-Dimensional Data Collection under Local Differential Privacy A Mansbridge, G Barbour, D Piras, M Murray, C Frye, I Feige, D Barber arXiv preprint arXiv:2010.12464, 2020 | 7* | 2020 |
| Large-scale calibration and simulation of COVID-19 epidemiologic scenarios to support healthcare planning N Groves-Kirkby, E Wakeman, S Patel, R Hinch, T Poot, J Pearson, ... Epidemics 42, 100662, 2023 | 4 | 2023 |
| Task-specific experimental design for treatment effect estimation B Connolly, K Moore, T Schwedes, A Adam, G Willis, I Feige, C Frye International Conference on Machine Learning, 6384-6401, 2023 | 2 | 2023 |
| Improving latent variable descriptiveness by modelling rather than ad-hoc factors A Mansbridge, R Fierimonte, I Feige, D Barber Machine Learning 108, 1601-1611, 2019 | 2* | 2019 |
