Dual query: Practical private query release for high dimensional data

31st International Conference on Machine Learning, ICML 2014

Volumn 4, Issue , 2014, Pages 2908-2916

  Gaboardi, Marco ^a   Arias, Emilio Jesús Gauego ^b   Hsu, Justin ^b   Aaron, Roth ^b   Wu, Zhiwei Steven ^b  

^a UNIVERSITY OF DUNDEE   (United Kingdom)

^b UNIVERSITY OF PENNSYLVANIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; CLUSTERING ALGORITHMS; INTEGER PROGRAMMING; LEARNING SYSTEMS;

HIGH DIMENSIONAL DATA; HIGH DIMENSIONAL DATASETS; INTEGER PROGRAM; MULTIPLE ORDERS; NETFLIX; STATE OF THE ART; WORST-CASE COMPLEXITY;

QUERY PROCESSING;

EID: 84919791361     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (37)

1. Bache, K. and Lichman, M. UCI machine learning repository, 2013.
2. Beimel, Amos, Nissim, Kobbi, and Stemmer, Uri. Characterizing the sample complexity of private learners. In ACM SIGACT Innovations in Theoretical Computer Science (ITCS), Berkeley, California, pp. 97-110, 2013.
3. Blum, A., Ligett, K., and Roth, A. A learning theory approach to noninteractive database privacy. Journal of the ACM, 60(2): 12, 2013.
4. Blum, Avrim, Dwork, Cynthia, McSherry, Frank, and Nissim, Kobbi. Practical privacy: The sulq framework. In ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems (PODS). Baltimore, Maryland, pp. 128- 138, 2005.
5. Chaudhuri, Kamalika and Hsu, Daniel. Sample complexity bounds for differentially private learning. Journal of Machine Learning Research, 19:155-186, 2011.
6. Chaudhuri, Kamalika and Monteleoni, Claire. Privacy-preserving logistic regression. In Conference on Neural Information Processing Systems (NIPS), Vancouver, British Colombia, pp. 289-296, 2008.
7. Chaudhuri, Kamalika and Vinterbo, Staal A. A stability-based validation procedure for differentially private machine learning. pp. 2652-2660, 2013.
8. Chaudhuri, Kamalika, Monteleoni, Claire, and Sarwate, Anand D. Differentially private empirical risk minimization. Journal of Machine Learning Research, 12:1069-1109, 2011.
9. Chaudhuri, Kamalika, Sarwate, Anand, and Sinha, Kaushik. Near-optimal differentially private principal components. In Conference on Neural Information Processing Systems (NIPS), Lake Tahoe, California, pp. 998-1006, 2012.
10. Duchi, J.C., Jordan, M.I., and Wainwright, M.J. Local privacy and statistical minimax rates. In IEEE Symposium on Foundations of Computer Science (FOCS), Berkeley, California, 2013.
11. Dwork, C., Naor, M., Reingold, O., Rothblum, G.N., and Vadhan, S.P. On the complexity of differentially private data release: efficient algorithms and hardness results. In ACM SIGACT Sym-posium on Theory of Computing (STOC), Bethesda, Maryland, pp. 381-390, 2009.
12. Dwork, C., Rothblum, G.N., and Vadhan, S. Boosting and differential privacy. In IEEE Symposium on Foundations of Computer Science (FOCS), Las Vegas, Nevada, pp. 51-60, 2010.
13. Dwork, Cynthia, McSherry, Frank, Nissim, Kobbi, and Smith, Adam. Calibrating noise to sensitivity in private data analysis. In IACR Theory of Cryptography Conference (TCC), New York, New York, pp. 265-284, 2006.
14. Dwork, Cynthia, Nikolov, Aleksandar, and Talwar, Kunal. Using convex relaxations for efficiently and privately releasing marginals. In SIGACT - SIGGRAPH Symposium on Computational Geometry (SOCG), Kyoto, Japan, pp. 261, 2014.
15. Freund, Y. and Schapire, R.E. Game theory, on-line prediction and boosting. In Conference on Computational Learning Theory (CoLT), Desenzano sul Garda, Italy, pp. 325-332, 1996.
16. Gaboardi, Marco, Gallego Arias, Emilio Jesus, Hsu, Justin, Roth, Aaron, and Wu, Zhiwei Steven. Dual query: Practical private query release for high dimensional data. Technical report, 2014. http://arxiv.org/abs/1402.1526.
17. Gupta, A., Roth, A., and Ullman, J. Iterative constructions and private data release. In IACR Theory of Cryptography Conference (TCC), Taormina, Italy, pp. 339-356, 2012.
18. Gupta, Anupam, Hardt, Moritz, Roth, Aaron, and Ullman, Jonathan. Privately releasing conjunctions and the statistical query barrier. SIAM Journal on Computing, 42(4): 1494-1520, 2013.
19. Hardt, Moritz and Rothblum, Guy N. A multiplicative weights mechanism for privacy-preserving data analysis. In IEEE Symposium on Foundations of Computer Science (FOCS), Las Ve-gas, Nevada, pp. 61-70, 2010.
20. Hardt, Moritz, Ligett, Katrina, and McSherry, Frank. A simple and practical algorithm for differentially private data release. In Conference on Neural Information Processing Systems (NIPS), Lake Tahoe, California, pp. 2348-2356, 2012.
21. Hsu, Justin, Roth, Aaron, and Ullman, Jonathan. Differential privacy for the analyst via private equilibrium computation. In ACM SIGACT Symposium on Theory of Computing (STOC), Palo Alto, California, pp. 341-350, 2013.
22. Kasiviswanathan, Shiva Prasad, Lee, Homin K., Nissim, Kobbi, Raskhodnikova, Sofya, and Smith, Adam. What can we learn privately? SIAM Journal on Computing, 40(3):793-826, 2011.
23. Kearns, Michael J. Efficient noise-tolerant learning from statistical queries. Journal of the ACM, 45(6):983-1006, 1998.
24. Kifer, Daniel, Smith, Adam, and Thakurta, Abhradeep. Private convex empirical risk minimization and high-dimensional regression. Journal of Machine Learning Research, 1:41, 2012.
25. Li, Chao and Miklau, Gerome. An adaptive mechanism for accurate query answering under differential privacy, volume 5, pp. 514-525, 2012.
26. Li, Chao, Hay, Michael, Rastogi, Vibhor, Miklau, Gerome, and McGregor, Andrew. Optimizing linear counting queries under differential privacy. In ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems (PODS), Indianapolis, Indiana, pp. 123-134, 2010.
27. McSherry, F. and Talwar, K. Mechanism design via differential privacy. In IEEE Symposium on Foundations of Computer Science (FOCS), Providence, Rhode Island, pp. 94-103, 2007.
28. Narayanan, A. and Shmatikov, V. Robust de-anonymization of large sparse datasets. In IEEE Symposium on Security and Privacy (S&P), Oakland, California, pp. 111-125, 2008.
29. Netflix. Netflix prize.
30. Roth, Aaron and Roughgarden, Tim. Interactive privacy via the median mechanism. In ACM SIGACT Symposium on Theory of Computing (STOC), Cambridge, Massachusetts, pp. 765-77411 .
31. Rubinstein, Benjamin I. P., Bartlett, Peter L., Huang, Ling, and Taft, Nina. Learning in a large function space: Privacy- preserving mechanisms for SVM learning. Journal of Privacy and Confidentiality, 4(1):4, 2012.
32. Thakurta, Abhradeep G. and Smith, Adam. (Nearly) optimal algorithms for private online learning in full-information and bandit settings. In Conference on Neural Information Processing Systems (NIPS), Lake Tahoe, California, pp. 2733-2741, 2013.
33. Thaler, Justin, Ullman, Jonathan, and Vadhan, Salil. Faster algorithms for privately releasing marginals. In International Colloquium on Automata, Languages and Programming (ICALP), Warwick, England, pp. 810-821, 2012.
34. 2+0(1) counting queries with differential privacy is hard. In ACM SIGACT Symposium on Theory of Computing (STOC), Palo Alto, California, pp. 361-370, 2013.
35. Ullman, J. and Vadhan, S.P. PCPs and the hardness of generating private synthetic data. In IACR Theory of Cryptography Conference (TCC), Providence, Rhode Island, pp. 400-416, 2011.
36. Yaroslavtsev, Grigory, Cormode, Graham, Procopiuc, Cecilia M., and Srivastava, Divesh. Accurate and efficient private release of datacubes and contingency tables. In IEEE International Conference on Data Engineering (ICDE), Brisbane, Australia, pp. 745-756, 2013.
37. Zhang, Jun, Cormode, Graham, Procopiuc, Cecilia M., Srivastava, Divesh, and Xiao, Xiaokui. Privbayes: Private data release via bayesian networks. In ACM SIGMOD International Conference on Management of Data (SIGMOD), Snowbird, Utah, 2014.