Differentially Private Feature Selection via Stability Arguments, and the Robustness of the Lasso

By Abhradeep Thakurta, Adam D. Smith. 2013

180 citations recorded by the source corpus.

Subfields: Statistics and Probability, Privacy & Security

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

In Privacy & Security

Citations in the corpus

Tight Lower Bounds for Differentially Private Selection (2017, background): “Selection problems appear in many natural statistical problems, including private multiple hypothesis testing [1], sparse linear regression [2], [3], finding frequent itemsets [4], and as subroutines in algorithms for answering exponentially many statistical queries [5], [6], [7], [8], [9], approxim”
Advanced Probabilistic Couplings for Differential Privacy (2016, neutral): “We demonstrate these rules on a classic example of accuracy-dependent privacy: the Propose-test-release framework [16, 48].”
Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds (2014, background): “[34], Smith and Thakurta [45] considered parameter convergence for high-dimensional sparse regression (where p n).”
Private Stochastic Convex Optimization with Optimal Rates (2019, background): “The problem of ERM with differential privacy (DP-ERM) has been well-studied and asymptotically tight upper and lower bounds on excess loss 1 are known [CM08, CMS11, JKT12, KST12, ST13, SCS13, DJW13, Ull15, JT14, BST14, TTZ15, STU17, WLK + 17, WYX17, INS + 19].”
Proving Differential Privacy in Hoare Logic (2014, background): “On a more practical side, it would be interesting to implement our transformation for a realistic setting, for instance modeling thePINQ language [30].”
Private Multiplicative Weights Beyond Linear Queries (2014, neutral): “Starting with the results of Dwork and Lei [10] and Chaudhuri, Monteleone, and Sarwate [8], there has been a long line of work [24, 27, 22, 3] showing how to compute an accurate and differentially private answer to a single CM query.”
Simultaneous Private Learning of Multiple Concepts (2015, methodology): “[1] R. Bassily, A. Smith, and A. Thakurta.”
Private selection from private candidates (2018, background): “Margin-based Mechanism Adist [3, 34] Suppose that each qi has sensitivity at most s .”
Nearly Optimal Private LASSO (2015, background): “First [20] and then [24] studied the LASSO estimator with differential privacy guarantee.”
Privacy-Preserving Distributed Multi-Task Learning with Asynchronous Updates (2017, methodology): “Thakurta and Smith [41] studied feature selection with stability property, whereas Xiao et al. [45] utilized wavelet transform which can be applied on both ordinal and nominal data.”