| Quality of uncertainty quantification for Bayesian neural network inference J Yao, W Pan, S Ghosh, F Doshi-Velez arXiv preprint arXiv:1906.09686, 2019 | 132 | 2019 |
| Promises and pitfalls of black-box concept learning models A Mahinpei, J Clark, I Lage, F Doshi-Velez, W Pan arXiv preprint arXiv:2106.13314, 2021 | 92 | 2021 |
| Cruds: Counterfactual recourse using disentangled subspaces M Downs, JL Chu, Y Yacoby, F Doshi-Velez, W Pan ICML WHI 2020, 1-23, 2020 | 69 | 2020 |
| Optimizing the multiclass F-measure via biconcave programming H Narasimhan, W Pan, P Kar, P Protopapas, HG Ramaswamy 2016 IEEE 16th international conference on data mining (ICDM), 1101-1106, 2016 | 58 | 2016 |
| Power constrained bandits J Yao, E Brunskill, W Pan, S Murphy, F Doshi-Velez Machine Learning for Healthcare Conference, 209-259, 2021 | 43 | 2021 |
| Ensembles of locally independent prediction models A Ross, W Pan, L Celi, F Doshi-Velez Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 5527-5536, 2020 | 43 | 2020 |
| Wide mean-field bayesian neural networks ignore the data B Coker, WP Bruinsma, DR Burt, W Pan, F Doshi-Velez International Conference on Artificial Intelligence and Statistics, 5276-5333, 2022 | 23 | 2022 |
| Failure modes of variational autoencoders and their effects on downstream tasks Y Yacoby, W Pan, F Doshi-Velez arXiv preprint arXiv:2007.07124, 2020 | 23 | 2020 |
| Learning qualitatively diverse and interpretable rules for classification AS Ross, W Pan, F Doshi-Velez arXiv preprint arXiv:1806.08716, 2018 | 16 | 2018 |
| Bacoun: Bayesian classifers with out-of-distribution uncertainty T Guénais, D Vamvourellis, Y Yacoby, F Doshi-Velez, W Pan arXiv preprint arXiv:2007.06096, 2020 | 15 | 2020 |
| What makes a good explanation?: A harmonized view of properties of explanations Z Chen, V Subhash, M Havasi, W Pan, F Doshi-Velez arXiv preprint arXiv:2211.05667, 2022 | 14 | 2022 |
| Deep variational transfer: Transfer learning through semi-supervised deep generative models M Belhaj, P Protopapas, W Pan arXiv preprint arXiv:1812.03123, 2018 | 11 | 2018 |
| Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights MF Pradier, W Pan, J Yao, S Ghosh, F Doshi-Velez arXiv preprint arXiv:1811.07006, 2018 | 11 | 2018 |
| Latent projection bnns: Avoiding weight-space pathologies by learning latent representations of neural network weights MF Pradier, W Pan, J Yao, S Ghosh, F Doshi-Velez Workshop on Bayesian Deep Learning, NIPS, 2018 | 11 | 2018 |
| Uncertainty-aware (una) bases for deep bayesian regression using multi-headed auxiliary networks S Thakur, C Lorsung, Y Yacoby, F Doshi-Velez, W Pan arXiv preprint arXiv:2006.11695, 2020 | 9 | 2020 |
| A characterization of the non-uniqueness of nonnegative matrix factorizations W Pan, F Doshi-Velez arXiv preprint arXiv:1604.00653, 2016 | 9 | 2016 |
| Soft prompting might be a bug, not a feature L Bailey, G Ahdritz, A Kleiman, S Swaroop, F Doshi-Velez, W Pan | 8 | 2023 |
| Wide mean-field variational bayesian neural networks ignore the data B Coker, W Pan, F Doshi-Velez arXiv preprint arXiv:2106.07052, 2021 | 8 | 2021 |
| Why do universal adversarial attacks work on large language models?: Geometry might be the answer V Subhash, A Bialas, W Pan, F Doshi-Velez The Second Workshop on New Frontiers in Adversarial Machine Learning, 2023 | 7 | 2023 |
| Idiographic Prediction of Suicidal Thoughts: Building Personalized Machine Learning Models with Real-Time Monitoring Data S Wang, Y Yacoby, W Pan, K Bentley, S Bird, R Buonopane, A Christie, ... PsyArXiv, 2023 | 7 | 2023 |