The balloon mean is a computationally tractable robust differentially private mean estimator with theoretical guarantees under heavy-tailed contaminated elliptical models.
In: Proceedings of the Thirty-ninth Annual AC M Symposium on Theory of Computing, pp
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
Optimal reconstruction error from approximate linear queries converges to sqrt(2d/(d+1)) delta as number of queries T goes to infinity, with doubly exponential excess error decay for fixed d and exp(d) queries needed for vanishing excess when d grows.
Improves exact algorithm for minimum edge deletion to connected cactus from O*(3^n) to O*(2^n), with O*(2^n n^{O(q)}) for q distinct nonnegative costs and O*(2^n (W+1)) pseudo-polynomial for integer costs summing to W.
A differentially private pipeline using node-level DP summaries to fit ERGMs or SBMs, generate synthetic networks, and simulate SIS disease spread on ARTNet sexual contact data produces incidence, prevalence, and intervention effect sizes close to non-private versions.
Empirical Bayes denoising of Gaussian mechanism outputs reduces MSE for differentially private histogram release, PCA, and linear regression.
CHRONOS is a three-layer system for evolving data marketplaces that applies neural-ODE temporal decay, changepoint-aware Shapley valuation, and EXP3-IX private coordination to achieve 0.937 recall, 2.74 qps, 161 ms latency, and epsilon 4.25 at delta 10^-6.
PAFER estimates statistical parity for differentially private decision trees using Laplacian noise, achieving low error while preserving privacy and favoring interpretable trees.
citing papers explorer
-
Optimal Reconstruction from Linear Queries
Optimal reconstruction error from approximate linear queries converges to sqrt(2d/(d+1)) delta as number of queries T goes to infinity, with doubly exponential excess error decay for fixed d and exp(d) queries needed for vanishing excess when d grows.
-
Enhancing Differentially Private Mechanisms via Empirical Bayes
Empirical Bayes denoising of Gaussian mechanism outputs reduces MSE for differentially private histogram release, PCA, and linear regression.
-
Privacy Constrained Fairness Estimation for Decision Trees
PAFER estimates statistical parity for differentially private decision trees using Laplacian noise, achieving low error while preserving privacy and favoring interpretable trees.