Private Empirical Risk Minimization, Revisited

By Raef Bassily, Adam D. Smith, Abhradeep Thakurta. 2014

51 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Privacy Amplification by Iteration (2018, background): “(†) THIS BOUND IS NOT STATED EXPLICITLY BUT CAN BE DERIVED BY SETTING THE PARAMETERS IN [23] APPROPRIATELY.”
Towards Practical Differentially Private Convex Optimization (2019, positive): “For reasonable values of the privacy parameters, the accuracy of the best private model is within 2% of the baseline for two of these datasets, essentially identical to the baseline for one of them, and even slightly higher than the baseline for one of the datasets! This provides empirical evidence ”
Differentially Private Model Publishing for Deep Learning (2019, methodology): “Differential privacy (DP), a defacto standard for privacy that offers provable privacy guarantees, has been applied for privacy-preserving machine learning [8], [10], [11], [32], [42].”
Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo (2015, methodology): “The boundedness on the loss-function (log-likelihood here) is a standard assumption in many DP works (Chaudhuri et al., 2011; Bassily et al., 2014; Song et al., 2013; Kifer et al., 2012).”
Private Multiplicative Weights Beyond Linear Queries (2014, background): “[24] D. Kifer, A. D. Smith, and A. Thakurta.”
Learning with Differential Privacy: Stability, Learnability and the Sufficiency and Necessity of ERM Principle (2015, methodology): “differentially private algorithms would be to approximately minimize the empirical risk using some differentially private procedures (Chaudhuri et al., 2011; Kifer et al., 2012; Bassily et al., 2014).”
How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy (2023, methodology): “Intuitively, the uncertainty of whether a sample has contributed can “help” the privacy of this sample, and a technique named privacy amplification by subsampling is widely used to achieve strong privacy-utility trade-offs for practical algorithms like DP-SGD (Bassily et al., 2014; Abadi et al., 201”
Lossless Compression of Efficient Private Local Randomizers (2021, background): “Mean estimation has attracted a lot of attention in recent years as it is an important subroutine in differentially private (stochastic) gradient descent algorithms (Bassily et al., 2014; Abadi et al., 2016) used in private federated learning (Kairouz et al.”
Differentially Private Federated Learning: An Information-Theoretic Perspective (2021, background): “, (Balle et al., 2019b; Bassily et al., 2014; 2019; Chaudhuri et al., 2011; Song et al., 2013; Wu et al., 2017)) can be viewed as a Gaussian kernel whose input (and output) are values from a compact set.”
Nearly Optimal Private LASSO (2015, background): “[2] recently show that in the private ERM setting, in general this polynomial dependence on p is unavoidable.”
Differentially Private Matrix Completion, Revisited (2017, methodology): “Our algorithm consistently outperforms (in terms of accuracy) the existing state-of-the-art DP matrix completion methods (SVD-based method by [43], and a variant of projected gradient descent [9, 4, 1]).”
A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergences (2020, unknown): “, [3– 6, 18, 21, 30].”
The Large Margin Mechanism for Differentially Private Maximization (2014, background): “There has been a large amount of work on differential privacy for a wide range of statistical and machine learning tasks over the last decade [6, 30, 13, 21, 33, 24, 1]; for overviews, see [18] and [29].”
Privacy-preserving Analysis of Correlated Data (2016, background): “…et al., 2006), and there is a growing body of work on differentially private learning algorithms (Chaudhuri et al., 2011; Jain et al., 2012; Kifer et al., 2012; Chaudhuri et al., 2012; Hardt and Roth, 2013; Wang et al., 2015; Duchi et al., 2013; Bassily et al., 2014; Imtiaz and Sarwate, 2015).”