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
Proceedings of the Forty-First Annual ACM Symposium on Theory of Computing , pages =
10 Pith papers cite this work, alongside 804 external citations. Polarity classification is still indexing.
10
Pith papers citing it
804
external citations · external index
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
SuperDP refutes ε-DP via simultaneous synthesis of input pairs and witness functions using upper expectation supermartingales and lower expectation submartingales, delivering the first fully automated, sound, and semi-complete method applicable to both discrete and continuous stochastic mechanisms.
A win-win reduction from worst-case decoding and distinguishing problems yields average-case LPN hardness at noise rate n to the minus alpha for any constant alpha less than 1.
PE-means extends private evolution to DP k-means clustering with new operators and achieves 26% average improvement in clustering loss over prior methods.
Continuous-Eris is a new separation logic that verifies exact samplers for the uniform, Gaussian, and Laplace distributions plus an exact real arithmetic library, with all proofs machine-checked in Rocq.
A 3D Pauli stabilizer Hamiltonian is constructed that encodes a qubit with exponential lifetime at finite temperature through recursive local transformations on a seed Hamiltonian.
Empirical Bayes denoising of Gaussian mechanism outputs reduces MSE for differentially private histogram release, PCA, and linear regression.
LEPA predicts geometrically transformed patch embeddings from context and transform parameters, lifting MRR from <0.2 (interpolation) to >0.8 while keeping competitive PANGAEA segmentation scores.
DQI resists classical simulation by locating high-probability outputs but is simulable at a low level of the polynomial hierarchy, constructively solves a MacWilliams-based coding bound, and corresponds to low-energy states of a quantum harmonic oscillator.
A model-agnostic framework combining GPBACC with robust aggregation and group testing for privacy-preserving and verifiable distributed learning in federated and decentralized settings.
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.
-
SuperDP: Differential Privacy Refutation via Supermartingales
SuperDP refutes ε-DP via simultaneous synthesis of input pairs and witness functions using upper expectation supermartingales and lower expectation submartingales, delivering the first fully automated, sound, and semi-complete method applicable to both discrete and continuous stochastic mechanisms.
-
Towards Worst-case Hardness for Low-Noise LPN
A win-win reduction from worst-case decoding and distinguishing problems yields average-case LPN hardness at noise rate n to the minus alpha for any constant alpha less than 1.
-
PE-means: Improved Differentially Private $k$-means Clustering through Private Evolution
PE-means extends private evolution to DP k-means clustering with new operators and achieves 26% average improvement in clustering loss over prior methods.
-
Verifying Exact Samplers for Continuous Distributions with a Discrete Program Logic
Continuous-Eris is a new separation logic that verifies exact samplers for the uniform, Gaussian, and Laplace distributions plus an exact real arithmetic library, with all proofs machine-checked in Rocq.
-
A passive self-correcting quantum memory in three dimensions
A 3D Pauli stabilizer Hamiltonian is constructed that encodes a qubit with exponential lifetime at finite temperature through recursive local transformations on a seed Hamiltonian.
-
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.
-
The Lov\'{a}sz Local Lemma: Foundations and Applications
LEPA predicts geometrically transformed patch embeddings from context and transform parameters, lifting MRR from <0.2 (interpolation) to >0.8 while keeping competitive PANGAEA segmentation scores.
-
On the Complexity of Decoded Quantum Interferometry
DQI resists classical simulation by locating high-probability outputs but is simulable at a low level of the polynomial hierarchy, constructively solves a MacWilliams-based coding bound, and corresponds to low-energy states of a quantum harmonic oscillator.
-
Privacy-Preserving and Verifiable Approximate Distributed Coded Computing
A model-agnostic framework combining GPBACC with robust aggregation and group testing for privacy-preserving and verifiable distributed learning in federated and decentralized settings.