Private Multiplicative Weights beyond Linear Queries

Proceedings of the ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems

Volumn 31, Issue , 2015, Pages 303-312

  Ullman, Jonathan ^a  

^a Columbia University ^*  (United States)

Author keywords

Convex Optimization; Differential Privacy; Statistical Estimation

Indexed keywords

ARTIFICIAL INTELLIGENCE; CONVEX OPTIMIZATION; DATABASE SYSTEMS; FUNCTIONS; LEARNING SYSTEMS; QUERY PROCESSING;

CONVEX FUNCTIONS; CONVEX MINIMIZATION; DIFFERENTIAL PRIVACIES; LOGISTIC REGRESSIONS; PRIVACY PRESERVING; SENSITIVE INFORMATIONS; STATISTICAL ESTIMATION;

DATA PRIVACY;

EID: 84955286201     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/2745754.2745755     Document Type: Conference Paper

References (30)

1. S. Arora, E. Hazan, and S. Kale. The multiplicative weights update method: a meta-Algorithm and applications. Theory of Computing, 8(1):121-164, 2012.
2. R. Bassily, A. Smith, T. Steinke, and J. Ullman. More general queries with better generalization error in adaptive data analysis. Manuscript, 2015.
3. R. Bassily, A. Smith, and A. Thakurta. Private empirical risk minimization, revisited. CoRR, abs/1405.7085, 2014.
4. A. Beimel, K. Nissim, and U. Stemmer. Private learning and sanitization: Pure vs. approximate differential privacy. In APPROX-RANDOM, pages 363-378. Springer, 21-23 August 2013.
5. A. Blum, K. Ligett, and A. Roth. A learning theory approach to non-interactive database privacy. In ACM Symposium on Theory of Computing (STOC '08), pages 609-618. ACM, 17-20 May 2008.
6. M. Bun, J. Ullman, and S. P. Vadhan. Fingerprinting codes and the price of approximate differential privacy. In ACM Symposium on Theory of Computing (STOC '14). ACM, 1-3 June 2014.
7. K. Chandrasekaran, J. Thaler, J. Ullman, and A. Wan. Faster private release of marginals on small databases. In Innovations in Theoretical Computer Science (ITCS '14), pages 387-402. ACM, 12-14 January 2014.
8. K. Chaudhuri, C. Monteleoni, and A. D. Sarwate. Differentially private empirical risk minimization. Journal of Machine Learning Research, 12:1069-1109, 2011.
9. C. Dwork, V. Feldman, M. Hardt, T. Pitassi, O. Reingold, and A. Roth. Preserving statistical validity in adaptive data analysis. In STOC. ACM, June 14-17 2015.
10. C. Dwork and J. Lei. Differential privacy and robust statistics. In ACM Symposium on Theory of Computing (STOC '09), pages 371-380. ACM, 31 May-2 June 2009.
11. C. Dwork, F. McSherry, K. Nissim, and A. Smith. Calibrating noise to sensitivity in private data analysis. In Theory of Cryptography (TCC '06), pages 265-284. Springer, 4-7 March 2006.
12. C. Dwork, M. Naor, O. Reingold, G. N. Rothblum, and S. P. Vadhan. On the complexity of differentially private data release: eficient algorithms and hardness results. In ACM Symposium on Theory of Computing (STOC '09), pages 381-390. ACM, 31 May-2 June 2009.
13. C. Dwork, A. Nikolov, and K. Talwar. Eficient algorithms for privately releasing marginals via convex relaxations. CoRR, abs/1308.1385, 2013.
14. C. Dwork and A. Roth. The algorithmic foundations of differential privacy. Foundations and Trends in Theoretical Computer Science, 9(3-4):211-407, 2014.
15. C. Dwork, G. N. Rothblum, and S. P. Vadhan. Boosting and differential privacy. In IEEE Symposium on Foundations of Computer Science (FOCS '10), pages 51-60. IEEE Computer Society, 23-26 October 2010.
16. A. Gupta, M. Hardt, A. Roth, and J. Ullman. Privately releasing conjunctions and the statistical query barrier. In ACM Symposium on Theory of Computing (STOC '11), pages 803-812. ACM, 6-8 June 2011.
17. A. Gupta, A. Roth, and J. Ullman. Iterative constructions and private data release. In Theory of Cryptography (TCC '12), pages 339-356. Springer, 19-21 March 2012.
18. M. Hardt, K. Ligett, and F. McSherry. A simple and practical algorithm for differentially private data release. In Neural Information Processing Systems (NIPS '12), pages 2348-2356, 3-6 December 2012.
19. M. Hardt and G. N. Rothblum. A multiplicative weights mechanism for privacy-preserving data analysis. In IEEE Symposium on Foundations of Computer Science (FOCS '10), pages 61-70. IEEE Computer Society, 23-26 October 2010.
20. M. Hardt, G. N. Rothblum, and R. A. Servedio. Private data release via learning thresholds. In ACM-SIAM Symposium on Discrete Algorithms (SODA '12), pages 168-187. SIAM, 17-19 January 2012.
21. M. Hardt and J. Ullman. Preventing false discovery in interactive data analysis is hard. In FOCS. IEEE, October 19-21 2014.
22. P. Jain and A. G. Thakurta. (near) dimension independent risk bounds for differentially private learning. In ICML, pages 476-484. JMLR.org, 21-26 June 2014.
23. S. P. Kasiviswanathan, M. Rudelson, and A. Smith. The power of linear reconstruction attacks. In SODA, pages 1415-1433. SIAM, 6-8 Jan 2013.
24. D. Kifer, A. D. Smith, and A. Thakurta. Private convex optimization for empirical risk minimization with applications to high-dimensional regression. In Conference on Learning Theory (COLT '12), pages 25.1-25.40. JMLR.org, 25-27 June 2012.
25. F. McSherry and K. Talwar. Mechanism design via differential privacy. In FOCS, pages 94-103. IEEE Computer Society, 20-23 October 2007.
26. A. Roth and T. Roughgarden. Interactive privacy via the median mechanism. In ACM Symposium on Theory of Computing (STOC '10), pages 765-774. ACM, 5-8 June 2010.
27. A. Thakurta and A. Smith. Differentially private feature selection via stability arguments, and the robustness of the lasso. In Conference on Learning Theory (COLT '13), pages 819-850. JMLR.org, 12-14 June 2013.
28. J. Thaler, J. Ullman, and S. P. Vadhan. Faster algorithms for privately releasing marginals. In International Colloquium on Automata, Languages, and Programming (ICALP '12), pages 810-821. Springer, 9-13 July 2012.
29. J. Ullman. Answering n2+o(1) counting queries with differential privacy is hard. In ACM Symposium on Theory of Computing (STOC '13), pages 361-370. ACM, 1-4 June 2013.
30. J. Ullman and S. P. Vadhan. PCPs and the hardness of generating private synthetic data. In Theory of Cryptography (TCC '11), pages 400-416. Springer, 28-30 March 2011.