Stochastic gradient descent with differentially private updates

Keywords

Differential privacy, Stochastic gradient descent, Scalability, Computer science, Computation

References

• Differential Privacy for Statistics: What we Know and What we Want to LearnCynthia Dwork, Adam Smith — 2010
• KDD-cup 99: knowledge discovery in a charitable organization's donor databaseSaharon Rosset, Aron Inger — 2000
• Testing Intrusion detection systemsJohn McHugh — 2000
• Differential privacy under continual observationCynthia Dwork, Moni Naor, Toniann Pitassi — 2010
• Practical privacy: the SuLQ frameworkAvrim Blum, Cynthia Dwork, Frank McSherry — 2005
• Differentially Private FilteringJérôme Le Ny, George J. Pappas — 2012
• Signal Processing and Machine Learning with Differential PrivacyAnand D. Sarwate, Kamalika Chaudhuri — 2013
• Differentially private Kalman filteringJérôme Le Ny, George J. Pappas — 2012
• Learning in a Large Function Space: Privacy-Preserving Mechanisms for SVM LearningBenjamin I. P. Rubinstein, Peter L. Bartlett, Ling Huang — 2009
• Privacy integrated queries: an extensible platform for privacy-preserving data analysisFrank McSherry — 2009
• Probabilistic Inference and Differential PrivacyOliver Williams, Frank McSherry — 2010
• Gradient-based learning applied to document recognitionYann LeCun, Léon Bottou, Yoshua Bengio — 1998
• Differentially Private Empirical Risk MinimizationKamalika Chaudhuri, Claire Monteleoni, Anand D. Sarwate — 2009
• Optimal Distributed Online Prediction Using Mini-BatchesOfer Dekel, Ran Gilad-Bachrach, Ohad Shamir — 2010
• Privacy Aware LearningJohn C. Duchi, Michael I. Jordan, Martin J. Wainwright — 2012
• A Differentially Private Stochastic Gradient Descent Algorithm for Multiparty ClassificationArun Rajkumar, Shivani Agarwal — 2012
• Calibrating Noise to Sensitivity in Private Data AnalysisCynthia Dwork, Frank McSherry, Kobbi Nissim — 2006
• Making Gradient Descent Optimal for Strongly Convex Stochastic OptimizationAlexander Rakhlin, Ohad Shamir, Karthik Sridharan — 2011
• Privacy: Theory meets Practice on the MapAshwin Machanavajjhala, Daniel Kifer, John M. Abowd — 2008
• Differentially Private Online LearningPrateek Jain, Pravesh K. Kothari, Abhradeep Thakurta — 2011

Cited by

• Protecting privacy of topology in consensus networksVaibhav Katewa, Aranya Chakrabortty, Vijay Gupta — 2015
• To Drop or Not to Drop: Robustness, Consistency and Differential Privacy Properties of DropoutPrateek Jain, Vivek Kulkarni, Abhradeep Thakurta — 2015
• Privacy for Free: Posterior Sampling and Stochastic Gradient Monte CarloYu-Xiang Wang, Stephen E. Fienberg, Alex Smola — 2015
• Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error BoundsRaef Bassily, Adam Smith, Abhradeep Thakurta — 2014
• Private Empirical Risk Minimization: Efficient Algorithms and Tight Error BoundsRaef Bassily, Adam Smith, Abhradeep Thakurta — 2014
• Learning from Data with Heterogeneous Noise using SGDShuang Song, Kamalika Chaudhuri, Anand D. Sarwate — 2014
• Differentially Private Distributed Convex Optimization via Functional PerturbationErfan Nozari, Pavankumar Tallapragada, Jorge Cortés — 2015
• Differentially Private Distributed Online LearningChencheng Li, Pan Zhou, Li Xiong — 2018
• Distributed optimal charging of electric vehicles for demand response and load shapingCaroline Le Floch, Francois Belletti, Samveg Saxena — 2015
• Distributed Differentially Private Stochastic Gradient Descent: An Empirical StudyIstván Hegedűs, Márk Jelasity — 2016
• Dimension Reduction Methods for Collaborative Mobile Gossip LearningÁrpád Berta, István Hegedűs, Márk Jelasity — 2016
• Optimal Charging of Electric Vehicles for Load Shaping: A Dual-Splitting Framework With Explicit Convergence BoundsCaroline Le Floch, Francois Belletti, Scott Moura — 2016
• Private Empirical Risk Minimization, RevisitedRaef Bassily, Adam Smith, Abhradeep Thakurta — 2014
• Differentially Private Stochastic Gradient Descent for in-RDBMS AnalyticsXi Wu, Arun Kumar, Kamalika Chaudhuri — 2016
• Deep Learning with Differential PrivacyMartı́n Abadi, Andy Chu, Ian Goodfellow — 2016
• COINSTAC: A Privacy Enabled Model and Prototype for Leveraging and Processing Decentralized Brain Imaging DataSergey Plis, Anand D. Sarwate, Dylan Wood — 2016
• Differentially Private Online Active Learning with Applications to Anomaly DetectionMohsen Ghassemi, Anand D. Sarwate, Rebecca N. Wright — 2016
• Variational Bayes In Private Settings (VIPS)Mijung Park, James R. Foulds, Kamalika Chaudhuri — 2016
• Privacy Preservation for Cloud-Based Data Sharing and Data AnalyticsYao Zheng — 2016
• Private Incremental RegressionShiva Prasad Kasiviswanathan, Kobbi Nissim, Hongxia Jin — 2017

Related papers

• Differential Privacy Machine Learning Based on Attention Residual NetworksYuming Cui, Jiangfeng Xu, Minghan Lian — 2023
• Accelerating Extreme Search Based on Natural Gradient Descent with Beta DistributionPavel Lyakhov, Ruslan Abdulkadirov — 2021
• Computational Complexity of Gradient Descent AlgorithmJ Nishchal, neel bhandari — 2021
• A backward SDE method for uncertainty quantification in deep learningRichard Archibald, Feng Bao, Yanzhao Cao — 2022
• Training a Two-Layer ReLU Network AnalyticallyAdrian Barbu — 2023
• Computational Complexity of Gradient Descent AlgorithmJ Nishchal, neel bhandari — 2021