privacy amplification

Improving the Convergence of Private Shuffled Gradient Methods with Public Data UAI 2026 Balls-and-Bins Sampling for DP-SGD AISTATS 2025 Leveraging Randomness in Model and Data Partitioning for Privacy Amplification ICML 2025 Mixing Times and Privacy Analysis for the Projected Langevin Algorithm under a Modulus of Continuity JMLR 2025 Near-Exact Privacy Amplification for Matrix Mechanisms ICLR 2025 Noisy SIGNSGD Is More Differentially Private Than You (Might) Think ICML 2025 Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting ICML 2025 Privacy Amplification Through Synthetic Data: Insights from Linear Regression ICML 2025 Scaling up the Banded Matrix Factorization Mechanism for Large Scale Differentially Private ML ICLR 2025 A Generalized Shuffle Framework for Privacy Amplification: Strengthening Privacy Guarantees and Enhancing Utility AAAI 2024 Confidential-DPproof: Confidential Proof of Differentially Private Training ICLR 2024 Differentially Private Graph Diffusion with Applications in Personalized PageRanks NeurIPS 2024 Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement NeurIPS 2024 On Differentially Private Federated Linear Contextual Bandits ICLR 2024 Privacy Amplification by Iteration for ADMM with (Strongly) Convex Objective Functions AAAI 2024 Privacy Amplification for Matrix Mechanisms ICLR 2024 Shifted Interpolation for Differential Privacy ICML 2024 Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification NeurIPS 2024 (Amplified) Banded Matrix Factorization: A unified approach to private training NeurIPS 2023 Breaking the Communication-Privacy-Accuracy Tradeoff with f-Differential Privacy NeurIPS 2023 Echo of Neighbors: Privacy Amplification for Personalized Private Federated Learning with Shuffle Model AAAI 2023 From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning ICML 2023 Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy NeurIPS 2023 Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation NeurIPS 2023 Differentially Private Learning Needs Hidden State (Or Much Faster Convergence) NeurIPS 2022