(Near) dimension independent risk bounds for differentially private learning

31st International Conference on Machine Learning, ICML 2014

Volumn 1, Issue , 2014, Pages 728-739

  Jain, Prateek ^a   Thakurta, Abhradeep ^b  

^a MICROSOFT RESEARCH   (United States)

^b STANFORD UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; ARTIFICIAL INTELLIGENCE; DATA PRIVACY; E-LEARNING; FUNCTIONS; LEARNING SYSTEMS; SOCIAL NETWORKING (ONLINE);

COMPUTATIONALLY EFFICIENT; EXPLICIT DEPENDENCES; GENERALIZED LINEAR MODEL; LOGARITHMIC DEPENDENCE; ON-LINE LEARNING METHODS; PRIVACY PRESERVING; STRONG CONVEXITIES; STRUCTURAL ASSUMPTION;

RISK PERCEPTION;

EID: 84919831631     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (24)

1. Chaudhuri, Kamalika and Hsu, Daniel. Sample complexity bounds for differentially private learning. Journal of Ma chine Learning Research-Proceedings Track, 19:155-186, 2011.
2. Chaudhuri, Kamalika and Monteleoni, Claire. Privacy-preserving logistic regression. In NIPS, 2008.
3. Chaudhuri, Kamalika, Monteleoni, Claire, and Sarwate, Anand D. Differentially private empirical risk minimiza tion. JMLR, 12:1069-1109, 2011.
4. Duchi, John C, Jordan, Michael I., and Wainwright, Mar tin J. Privacy aware learning. In NIPS, 2012.
5. Dwork, Cynthia, Kenthapadi, Krishnaram, McSherry, Frank, Mironov, Ilya, and Naor, Moni. Our data, our selves: Privacy via distributed noise generation. In EU-ROCRYPT, 2006a.
6. Dwork, Cynthia, McSherry, Frank, Nissim, Kobbi, and Smith, Adam. Calibrating noise to sensitivity in private data analysis. In TCC, 2006b.
7. Dwork, Cynthia, Naor, Moni, Pitassi, Toniann, and Rothblum, Guy N. Differential privacy under continual ob servation. In STOC, 2010a.
8. Dwork, Cynthia, Naor, Moni, Pitassi, Toniann, and Rothblum, Guy N. Differential privacy under continual ob servation. In Proceedings of the 42nd ACM symposium on Theory of computing, 2010b.
9. Dwork, Cynthia, Rothblum, Guy N, and Vadhan, Salil. Boosting and differential privacy. In FOCS, 2010c.
10. Hazan, Elad, Agarwal, Amit, and Kale, Satyen. Loga rithmic regret algorithms for online convex optimization. Machine Learning, 2007.
11. Jain, Prateek and Thakurta, Abhradeep. Differentially pri vate kernel learning. In ICML, 2013.
12. Jain, Prateek, Kothari, Pravesh, and Thakurta, Abhradeep. Differentially private online learning. In COLT, 2012.
13. Kakade, Sham M, Sridharan, Karthik, and Tewari, Ambuj. On the complexity of linear prediction: Risk bounds, margin bounds, and regularization. In NIPS, 2008.
14. Kasiviswanathan, Shiva Prasad and Smith, Adam. A note on differential privacy: Defining resistance to arbitrary side information. CoRR, arXiv:0803.39461 [cs.CR], 2008.
15. Kifer, Daniel, Smith, Adam, and Thakurta, Abhradeep. Private convex empirical risk minimization and high-dimensional regression. In COLT, 2012.
16. McSherry, Frank and Talwar, Kunal. Mechanism design via differential privacy. In FOCS, 2007.
17. Negahban, Sahand, Ravikumar, Pradeep, Wainwright, Martin J., and Yu, Bin. A unified framework for high-dimensional analysis of $m$-estimators with decompos able regularizes. In NIPS, 2009.
18. Pathak, Manas A., Rane, Shantanu, and Raj, Bhiksha. Multiparty differential privacy via aggregation of locally trained classifiers. In NIPS, 2010.
19. Rubinstein, Benjamin IP, Bartlett, Peter L, Huang, Ling, and Taft, Nina. Learning in a large function space: Privacy-preserving mechanisms for svm learning. arXiv preprint arXiv:0911.5708, 2009.
20. Shalev-Shwartz, Shai. Online learning and online con vex optimization. Foundations and Trends® in Machine Learning, 2011.
21. Shalev-Shwartz, Shai, Shamir, Ohad, Srebro, Nathan, and Sridharan, Karthik. Stochastic Convex Optimization. In COLT, 2009.
22. Smith, Adam and Thakurta, Abhradeep. Differentially pri vate feature selection via stability arguments, and the ro bustness of the lasso. In COLT, 2013.
23. Thakurta, Abhradeep Guha. Differentially private convex optimization for empirical risk minimization and high-dimensional regression. PhD Dissertation, 2013.
24. Zhang, Tong. Covering number bounds of certain regular ized linear function classes. Journal of Machine Learning Research, 2:527-550, 2002.