Differential Privacy

Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions UAI 2026 Characterizing Online and Private Learnability under Distributional Constraints via Generalized Smoothness COLT 2026 Differentially Private Approval-Based Committee Voting UAI 2026 DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models CVPR 2026 On the Curse of Dimensionality in Private Sparse Covariance Estimation and PCA COLT 2026 Private Linear Regression via a Down-Sensitivity to Privacy Reduction COLT 2026 Privately Estimating Black-Box Statistics COLT 2026 Ripple Mechanisms for Discrete and Private Statistics COLT 2026 Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning CVPR 2026 Almost linear time differentially private release of synthetic graphs AISTATS 2025 Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness ICLR 2025 Differentially Private Continual Release of Histograms and Related Queries AISTATS 2025 Distribution-Aware Mean Estimation under User-level Local Differential Privacy AISTATS 2025 Enhancing Learning with Label Differential Privacy by Vector Approximation ICLR 2025 Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization AAAI 2025 Locally Private Estimation with Public Features AISTATS 2025 Nearly Optimal Differentially Private ReLU Regression UAI 2025 Optimality of Matrix Mechanism on ℓ_p^p-metric ICLR 2025 Privacy in Metalearning and Multitask Learning: Modeling and Separations AISTATS 2025 Privately Counting Partially Ordered Data ICLR 2025 Private Mechanism Design via Quantile Estimation ICLR 2025 Scaling up the Banded Matrix Factorization Mechanism for Large Scale Differentially Private ML ICLR 2025 Approximate Kernel Density Estimation under Metric-based Local Differential Privacy UAI 2024 Confidential-DPproof: Confidential Proof of Differentially Private Training ICLR 2024 Differentially Private Deep Learning with Importance-based Adaptive Gradient Processing ACML 2024