Explanations based on the missing: Towards contrastive explanations with pertinent negatives A Dhurandhar, PY Chen, R Luss, CC Tu, P Ting, K Shanmugam, P Das Advances in neural information processing systems 31, 2018 | 715 | 2018 |
One explanation does not fit all: A toolkit and taxonomy of ai explainability techniques V Arya, RKE Bellamy, PY Chen, A Dhurandhar, M Hind, SC Hoffman, ... arXiv preprint arXiv:1909.03012, 2019 | 469 | 2019 |
Predicting abnormal returns from news using text classification R Luss, A d’Aspremont Quantitative Finance 15 (6), 999-1012, 2015 | 197 | 2015 |
Support vector machine classification with indefinite kernels R Luss, A d'Aspremont Advances in neural information processing systems 20, 2007 | 178 | 2007 |
Conditional gradient algorithmsfor rank-one matrix approximations with a sparsity constraint R Luss, M Teboulle siam REVIEW 55 (1), 65-98, 2013 | 122 | 2013 |
Ai explainability 360 toolkit V Arya, RKE Bellamy, PY Chen, A Dhurandhar, M Hind, SC Hoffman, ... Proceedings of the 3rd ACM India Joint International Conference on Data …, 2021 | 101 | 2021 |
Leveraging latent features for local explanations R Luss, PY Chen, A Dhurandhar, P Sattigeri, Y Zhang, K Shanmugam, ... Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data …, 2021 | 85* | 2021 |
One explanation does not fit all: a toolkit and taxonomy of AI explainability techniques (2019) V Arya, RKE Bellamy, PY Chen, A Dhurandhar, M Hind, SC Hoffman, ... URL https://arxiv. org/abs, 1909 | 77 | 1909 |
Efficient regularized isotonic regression with application to gene–gene interaction search R Luss, S Rosset, M Shahar | 72 | 2012 |
Clustering and feature selection using sparse principal component analysis R Luss, A d’Aspremont Optimization and Engineering 11, 145-157, 2010 | 72 | 2010 |
Beyond backprop: Online alternating minimization with auxiliary variables A Choromanska, B Cowen, S Kumaravel, R Luss, M Rigotti, I Rish, ... International Conference on Machine Learning, 1193-1202, 2019 | 71 | 2019 |
Improving simple models with confidence profiles A Dhurandhar, K Shanmugam, R Luss, PA Olsen Advances in Neural Information Processing Systems 31, 2018 | 68 | 2018 |
Connecting algorithmic research and usage contexts: a perspective of contextualized evaluation for explainable AI QV Liao, Y Zhang, R Luss, F Doshi-Velez, A Dhurandhar Proceedings of the AAAI Conference on Human Computation and Crowdsourcing 10 …, 2022 | 67 | 2022 |
Stochastic gradient descent with biased but consistent gradient estimators J Chen, R Luss arXiv preprint arXiv:1807.11880, 2018 | 55 | 2018 |
Tip: Typifying the interpretability of procedures A Dhurandhar, V Iyengar, R Luss, K Shanmugam arXiv preprint arXiv:1706.02952, 2017 | 44 | 2017 |
Social media and customer behavior analytics for personalized customer engagements S Buckley, M Ettl, P Jain, R Luss, M Petrik, RK Ravi, C Venkatramani IBM Journal of Research and Development 58 (5/6), 7: 1-7: 12, 2014 | 35 | 2014 |
Generalized isotonic regression R Luss, S Rosset Journal of Computational and Graphical Statistics 23 (1), 192-210, 2014 | 33 | 2014 |
A formal framework to characterize interpretability of procedures A Dhurandhar, V Iyengar, R Luss, K Shanmugam arXiv preprint arXiv:1707.03886, 2017 | 26 | 2017 |
Orthogonal matching pursuit for sparse quantile regression A Aravkin, A Lozano, R Luss, P Kambadur 2014 IEEE international conference on data mining, 11-19, 2014 | 23 | 2014 |
Sparse quantile huber regression for efficient and robust estimation AY Aravkin, A Kambadur, AC Lozano, R Luss arXiv preprint arXiv:1402.4624, 2014 | 20 | 2014 |