Image de couverture de livre

Optimal Variance and Covariance Estimation under Differential Privacy in the Add-Remove Model and Beyond

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Takakura, Shokichi, Liew, Seng Pei, Hasegawa, Satoshi
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Data Structures and Algorithms
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Analysis of Shuffling Beyond Pure Local Differential Privacy
par: Takagi, Shun, et autres
Publié: (2026)

Accelerating Differentially Private Federated Learning via Adaptive Extrapolation
par: Takakura, Shokichi, et autres
Publié: (2025)

Differentially Private Sampling from Distributions via Wasserstein Projection
par: Takakura, Shokichi, et autres
Publié: (2026)

FedDuA: Doubly Adaptive Federated Learning
par: Takakura, Shokichi, et autres
Publié: (2025)

Nearly Optimal Robust Covariance and Scatter Matrix Estimation Beyond Gaussians
par: Novikov, Gleb
Publié: (2025)

On Purely Private Covariance Estimation
par: d'Orsi, Tommaso, et autres
Publié: (2025)

Prediction with Expert Advice under Local Differential Privacy
par: Jacobsen, Ben, et autres
Publié: (2025)

Beyond Spectral Clustering: Probabilistic Cuts for Differentiable Graph Partitioning
par: Ghriss, Ayoub
Publié: (2025)

Towards Optimal Differentially Private Regret Bounds in Linear MDPs
par: Sahu, Sharan
Publié: (2025)

Differentially Private and Scalable Estimation of the Network Principal Component
par: Khayatian, Alireza, et autres
Publié: (2025)

Improved Regret in Stochastic Decision-Theoretic Online Learning under Differential Privacy
par: Wu, Ruihan, et autres
Publié: (2025)

PLAN: Variance-Aware Private Mean Estimation
par: Aumüller, Martin, et autres
Publié: (2023)

Lower Bounds for Private Estimation of Gaussian Covariance Matrices under All Reasonable Parameter Regimes
par: Portella, Victor S., et autres
Publié: (2024)

Efficient and Provable Algorithms for Covariate Shift
par: Adil, Deeksha, et autres
Publié: (2025)

Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms
par: Li, Yi, et autres
Publié: (2024)

The Discrete Gaussian for Differential Privacy
par: Canonne, Clément L., et autres
Publié: (2020)

Tolerant Algorithms for Learning with Arbitrary Covariate Shift
par: Goel, Surbhi, et autres
Publié: (2024)

Private Edge Density Estimation for Random Graphs: Optimal, Efficient and Robust
par: Chen, Hongjie, et autres
Publié: (2024)

On the Price of Differential Privacy for Hierarchical Clustering
par: Deng, Chengyuan, et autres
Publié: (2025)

Improved Robust Estimation for Erdős-Rényi Graphs: The Sparse Regime and Optimal Breakdown Point
par: Chen, Hongjie, et autres
Publié: (2025)

Robust Sparse Estimation for Gaussians with Optimal Error under Huber Contamination
par: Diakonikolas, Ilias, et autres
Publié: (2024)

Private Mean Estimation with Person-Level Differential Privacy
par: Agarwal, Sushant, et autres
Publié: (2024)

Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy
par: Dvijotham, Krishnamurthy, et autres
Publié: (2024)

High-Probability Bounds For Heterogeneous Local Differential Privacy
par: Aliakbarpour, Maryam, et autres
Publié: (2025)

Edgeworth Accountant: An Analytical Approach to Differential Privacy Composition
par: Wang, Hua, et autres
Publié: (2022)

Fast John Ellipsoid Computation with Differential Privacy Optimization
par: Li, Xiaoyu, et autres
Publié: (2024)

Optimal Robust Estimation under Local and Global Corruptions: Stronger Adversary and Smaller Error
par: Pittas, Thanasis, et autres
Publié: (2024)

Tight Bounds for Gaussian Mean Estimation under Personalized Differential Privacy
par: Dong, Wei, et autres
Publié: (2026)

Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent
par: Yu, Da, et autres
Publié: (2022)

Differentially Private Bootstrap: New Privacy Analysis and Inference Strategies
par: Wang, Zhanyu, et autres
Publié: (2022)

Learning-Augmented Moment Estimation on Time-Decay Models
par: Nagawanshi, Soham, et autres
Publié: (2026)

Ads that Stick: Near-Optimal Ad Optimization through Psychological Behavior Models
par: Darmasubramanian, Kailash Gopal, et autres
Publié: (2025)

Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond
par: Axiotis, Kyriakos, et autres
Publié: (2024)

Differential privacy from axioms
par: Blanc, Guy, et autres
Publié: (2025)

Differentially Private Learning Beyond the Classical Dimensionality Regime
par: Dwork, Cynthia, et autres
Publié: (2024)

Differentially Private Kernel Density Estimation
par: Liu, Erzhi, et autres
Publié: (2024)

Thompson Sampling Itself is Differentially Private
par: Ou, Tingting, et autres
Publié: (2024)

Near-Optimal Algorithms for Omniprediction
par: Okoroafor, Princewill, et autres
Publié: (2025)

On Computing Optimal Tree Ensembles
par: Komusiewicz, Christian, et autres
Publié: (2023)

Robust Learning with Optimal Error
par: Blanc, Guy
Publié: (2026)