Local privacy mechanisms preserve rate-double-robustness, enabling unbiased and semiparametrically efficient inference on target parameters indexed linearly by infinite-dimensional and nonlinearly by low-dimensional components from noisy private data.
hub
Tim Van Erven and Peter Harremos
22 Pith papers cite this work, alongside 1,062 external citations. Polarity classification is still indexing.
22
Pith papers citing it
1,062
external citations · Crossref
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Minimax sample complexity for uniform L_infty estimation is Theta(n^{d+1}) for degree-d polynomials and Theta(ns^2) for s-sparse Fourier-Walsh polynomials under noise, exceeding noiseless rates by factors of n and s.
Conditional lower bounds prove that exact local-query auditing of near-optimal policies requires Ω(2^{Hopt^F(ε)}) queries when occupancy Rashomon capacity is realized by a sparse-signature packing.
Derives non-asymptotic error bounds for standard, defensive, and self-normalized importance sampling with random KDE proposals from geometrically ergodic Markov chains, separating n^{-1/2} Monte Carlo error from MIAE/MISE proposal error.
Polynomial-time SDP and ellipsoid-based approximation of Kolmogorov widths yields efficient robust detection boundaries matching upper bounds up to polylog factors for structured constrained signals.
Bayesian PINNs for elliptic PDEs have posteriors that contract around the true solution at near-optimal rates, with the prior adapting automatically to unknown smoothness.
Constructs a minimax-optimal adaptive test for constant volatility in the nonparametric Gaussian white noise model under infill asymptotics, measuring deviations via the ratio of sigma(t) to its L2-average.
Profile MLE for the regime-switching threshold in null-recurrent diffusion converges at rate n^{-(1+γ)/2} to the arg sup of a doubly stochastic drifted Poisson process involving local time of oscillating Brownian motion.
DP-GD achieves minimax optimal non-asymptotic risk O(γ + γ²/ρ²) for well-conditioned high-dimensional data and power-law scaling for ill-conditioned power-law spectra, with the exponent depending on the privacy parameter ρ.
Optimal rates for non-log-concave sampling and log-partition estimation are sometimes equal to or faster than optimization rates, but polynomial-time algorithms fall short of near-optimal performance.
Introduces and implements confidence sequences for online statistical model checking of MDPs that require 50x fewer samples than prior state-of-the-art union-bound approaches.
Proves finite-shot mean-squared-error laws for virtual distillation and symmetry verification that define certified operating windows and a selection trichotomy for their comparison.
Derives closed-form optimal counterfactually fair regressor via barycentric quantile map and proves Õ(n^{-1/3}) finite-sample fairness and risk bounds for discretized post-processing under mild assumptions.
Near-linear time algorithm for robust regression under Gaussian covariates achieves O(sqrt(ε κ)) error with Õ(d/ε⁴) samples when ε κ ≲ 1, plus SQ and low-degree lower bounds.
Out-of-distribution extrapolation is non-identifiable from in-distribution data alone; the feature map, label map, and model class supply the identifiability bias that determines whether a network succeeds or fails at OOD generalization.
MoFI-FLR recovers active covariates and identifies their true functional forms (simple or complex) in high-dimensional functional linear regressions.
A semi-supervised kernel two-sample test integrates unlabeled covariate data to achieve asymptotic normality under the null, higher power than standard kernel tests, and consistency against fixed and local alternatives.
DSL uses doubly robust pseudo-outcomes and a multi-output neural network to jointly estimate time-varying conditional average treatment effects for right-censored survival data.
A semiparametric robust estimator for population location models the dominant component parametrically and the background nonparametrically, with FFT acceleration for scalable likelihood maximization.
A post-processing algorithm achieves distribution-free finite-sample group fairness guarantees with controlled excess risk for both group-aware and group-blind settings, shown minimax-optimal up to logs via lower bound.
An optimal transport method is proposed to construct confidence intervals with improved coverage, including theoretical consistency results, error bounds, and simulation comparisons.
citing papers explorer
-
Private Rate-Double-Robust Inference
Local privacy mechanisms preserve rate-double-robustness, enabling unbiased and semiparametrically efficient inference on target parameters indexed linearly by infinite-dimensional and nonlinearly by low-dimensional components from noisy private data.