| Discovering frequent patterns in sensitive data R Bhaskar, S Laxman, A Smith, A Thakurta Proceedings of the 16th ACM SIGKDD international conference on Knowledge …, 2010 | 200 | 2010 |
| GUPT: privacy preserving data analysis made easy P Mohan, A Thakurta, E Shi, D Song, D Culler Proceedings of the 2012 ACM SIGMOD International Conference on Management of …, 2012 | 180 | 2012 |
| Private convex empirical risk minimization and high-dimensional regression D Kifer, A Smith, A Thakurta Conference on Learning Theory, 25.1-25.40, 2012 | 134 | 2012 |
| Private empirical risk minimization: Efficient algorithms and tight error bounds R Bassily, A Smith, A Thakurta 2014 IEEE 55th Annual Symposium on Foundations of Computer Science, 464-473, 2014 | 133 | 2014 |
| Differentially private online learning P Jain, P Kothari, A Thakurta Conference on Learning Theory, 24.1-24.34, 2012 | 100 | 2012 |
| Analyze gauss: optimal bounds for privacy-preserving principal component analysis C Dwork, K Talwar, A Thakurta, L Zhang Proceedings of the forty-sixth annual ACM symposium on Theory of computing …, 2014 | 95 | 2014 |
| Differentially private feature selection via stability arguments, and the robustness of the lasso AG Thakurta, A Smith Conference on Learning Theory, 819-850, 2013 | 71 | 2013 |
| Differentially private learning with kernels P Jain, A Thakurta | 63 | 2013 |
| Noiseless database privacy R Bhaskar, A Bhowmick, V Goyal, S Laxman, A Thakurta International Conference on the Theory and Application of Cryptology and …, 2011 | 50 | 2011 |
| Practical locally private heavy hitters R Bassily, K Nissim, U Stemmer, AG Thakurta Advances in Neural Information Processing Systems, 2288-2296, 2017 | 40 | 2017 |
| Differentially private empirical risk minimization: Efficient algorithms and tight error bounds R Bassily, A Smith, A Thakurta arXiv preprint arXiv:1405.7085, 2014 | 33 | 2014 |
| Is interaction necessary for distributed private learning? A Smith, A Thakurta, J Upadhyay 2017 IEEE Symposium on Security and Privacy (SP), 58-77, 2017 | 29 | 2017 |
| Nearly optimal private lasso K Talwar, AG Thakurta, L Zhang Advances in Neural Information Processing Systems, 3025-3033, 2015 | 27 | 2015 |
| Private empirical risk minimization, revisited R Bassily, A Smith, A Thakurta arXiv preprint arXiv:1405.7085, 2014 | 23 | 2014 |
| To drop or not to drop: Robustness, consistency and differential privacy properties of dropout P Jain, V Kulkarni, A Thakurta, O Williams arXiv preprint arXiv:1503.02031, 2015 | 17 | 2015 |
| Private empirical risk minimization beyond the worst case: The effect of the constraint set geometry K Talwar, A Thakurta, L Zhang arXiv preprint arXiv:1411.5417, 2014 | 16 | 2014 |
| Testing the Lipschitz property over product distributions with applications to data privacy K Dixit, M Jha, S Raskhodnikova, A Thakurta Theory of Cryptography, 418-436, 2013 | 16 | 2013 |
| Learning new words AG Thakurta, AH Vyrros, US Vaishampayan, G Kapoor, J Freudiger, ... US Patent 9,594,741, 2017 | 14 | 2017 |
| (Near) dimension independent risk bounds for differentially private learning P Jain, AG Thakurta International Conference on Machine Learning, 476-484, 2014 | 10 | 2014 |
| (Nearly) optimal algorithms for private online learning in full-information and bandit settings AG Thakurta, A Smith Advances in Neural Information Processing Systems, 2733-2741, 2013 | 9 | 2013 |
Adam SmithProfessor of Computer Science, Boston UniversityVerified email at bu.edu