{"total":90,"rows":[{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412,"area":null},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400,"area":null},{"id":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224,"area":null},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88,"area":null},{"id":"2102.12677","title":"Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning","created":"2021-02-25","cited_by_count":86,"area":null},{"id":"2203.11481","title":"Mixed Differential Privacy in Computer Vision","created":"2022-03-22","cited_by_count":54,"area":null},{"id":"2212.01539","title":"Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping","created":"2022-12-03","cited_by_count":52,"area":null},{"id":"2112.00193","title":"Public Data-Assisted Mirror Descent for Private Model Training","created":"2021-12-01","cited_by_count":49,"area":null},{"id":"2106.13756","title":"Private Adaptive Gradient Methods for Convex Optimization","created":"2021-06-25","cited_by_count":46,"area":null},{"id":"2107.11136","title":"High Dimensional Differentially Private Stochastic Optimization with Heavy-tailed Data","created":"2021-07-23","cited_by_count":42,"area":null},{"id":"2202.05963","title":"Private Adaptive Optimization with Side Information","created":"2022-02-12","cited_by_count":38,"area":null},{"id":"2302.09483","title":"Why Is Public Pretraining Necessary for Private Model Training?","created":"2023-02-19","cited_by_count":37,"area":null},{"id":"2405.16002","title":"Does SGD really happen in tiny subspaces?","created":"2024-05-25","cited_by_count":36,"area":null},{"id":"2202.07178","title":"Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacy","created":"2022-02-15","cited_by_count":33,"area":null},{"id":"2204.07667","title":"Just Fine-tune Twice: Selective Differential Privacy for Large Language Models","created":"2022-04-15","cited_by_count":32,"area":null},{"id":"2208.07984","title":"Private Estimation with Public Data","created":"2022-08-16","cited_by_count":32,"area":null},{"id":"2102.03013","title":"Fast and Memory Efficient Differentially Private-SGD via JL Projections","created":"2021-02-05","cited_by_count":29,"area":null},{"id":"2406.02958","title":"PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs","created":"2024-06-05","cited_by_count":29,"area":null},{"id":"2310.09639","title":"DPZero: Private Fine-Tuning of Language Models without Backpropagation","created":"2023-10-14","cited_by_count":26,"area":null},{"id":"2305.13865","title":"Selective Pre-training for Private Fine-tuning","created":"2023-05-23","cited_by_count":23,"area":null},{"id":"2110.08557","title":"DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy","created":"2021-10-16","cited_by_count":20,"area":null},{"id":"2212.00309","title":"Differentially Private Adaptive Optimization with Delayed Preconditioners","created":"2022-12-01","cited_by_count":18,"area":null},{"id":"2103.01294","title":"Wide Network Learning with Differential Privacy","created":"2021-03-01","cited_by_count":17,"area":null},{"id":"2302.12448","title":"Subspace based Federated Unlearning","created":"2023-02-24","cited_by_count":17,"area":"safety"},{"id":"2106.00001","title":"Privately Learning Subspaces","created":"2021-05-28","cited_by_count":16,"area":null},{"id":"2303.01256","title":"Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance","created":"2023-03-02","cited_by_count":16,"area":null},{"id":"2308.06239","title":"Private Distribution Learning with Public Data: The View from Sample Compression","created":"2023-08-11","cited_by_count":14,"area":null},{"id":"2110.03450","title":"Efficient and Private Federated Learning with Partially Trainable Networks","created":"2021-10-06","cited_by_count":13,"area":null},{"id":"2305.05900","title":"DPMLBench: Holistic Evaluation of Differentially Private Machine Learning","created":"2023-05-10","cited_by_count":13,"area":null},{"id":"2108.00331","title":"Faster Rates of Private Stochastic Convex Optimization","created":"2021-07-31","cited_by_count":12,"area":null},{"id":"2306.00127","title":"Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning","created":"2023-05-31","cited_by_count":11,"area":null},{"id":"2110.11688","title":"Differentially Private Coordinate Descent for Composite Empirical Risk Minimization","created":"2021-10-22","cited_by_count":10,"area":null},{"id":"2306.03962","title":"PILLAR: How to make semi-private learning more effective","created":"2023-06-06","cited_by_count":10,"area":null},{"id":"2310.08425","title":"Differentially Private Non-convex Learning for Multi-layer Neural Networks","created":"2023-10-12","cited_by_count":10,"area":null},{"id":"2311.14056","title":"DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Release","created":"2023-11-23","cited_by_count":10,"area":"safety"},{"id":"2306.15056","title":"Optimal Differentially Private Model Training with Public Data","created":"2023-06-26","cited_by_count":9,"area":null},{"id":"2406.03519","title":"Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning","created":"2024-06-05","cited_by_count":9,"area":null},{"id":"2112.00845","title":"Improving Differentially Private SGD via Randomly Sparsified Gradients","created":"2021-12-01","cited_by_count":8,"area":null},{"id":"2201.03064","title":"Stability Based Generalization Bounds for Exponential Family Langevin Dynamics","created":"2022-01-09","cited_by_count":8,"area":null},{"id":"2205.13655","title":"Mixed Federated Learning: Joint Decentralized and Centralized Learning","created":"2022-05-26","cited_by_count":8,"area":null},{"id":"2402.18752","title":"Pre-training Differentially Private Models with Limited Public Data","created":"2024-02-28","cited_by_count":8,"area":null},{"id":"2403.07797","title":"Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Data","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2211.13403","title":"Differentially Private Image Classification from Features","created":"2022-11-24","cited_by_count":7,"area":null},{"id":"2310.15454","title":"Private Learning with Public Features","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2402.09483","title":"Oracle-Efficient Differentially Private Learning with Public Data","created":"2024-02-13","cited_by_count":6,"area":null},{"id":"2403.03856","title":"Public-data Assisted Private Stochastic Optimization: Power and Limitations","created":"2024-03-06","cited_by_count":6,"area":null},{"id":"2110.15252","title":"Federated Learning with Heterogeneous Differential Privacy","created":"2021-10-28","cited_by_count":5,"area":null},{"id":"2302.12559","title":"From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning","created":"2023-02-24","cited_by_count":5,"area":null},{"id":"2303.04612","title":"Differential Privacy Meets Neural Network Pruning","created":"2023-03-08","cited_by_count":5,"area":null},{"id":"2306.00920","title":"Better Private Linear Regression Through Better Private Feature Selection","created":"2023-06-01","cited_by_count":5,"area":null},{"id":"2312.15551","title":"On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift","created":"2023-12-24","cited_by_count":5,"area":null},{"id":"2401.06604","title":"Identifying Policy Gradient Subspaces","created":"2024-01-12","cited_by_count":5,"area":"deeprl"},{"id":"2405.17529","title":"Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2202.05089","title":"Backpropagation Clipping for Deep Learning with Differential Privacy","created":"2022-02-10","cited_by_count":4,"area":null},{"id":"2207.01560","title":"High-Dimensional Private Empirical Risk Minimization by Greedy Coordinate Descent","created":"2022-07-04","cited_by_count":4,"area":null},{"id":"2210.03843","title":"Differentially Private Deep Learning with ModelMix","created":"2022-10-07","cited_by_count":4,"area":null},{"id":"2406.02744","title":"DPDR: Gradient Decomposition and Reconstruction for Differentially Private Deep Learning","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2105.13637","title":"The Power of Sampling: Dimension-free Risk Bounds in Private ERM","created":"2021-05-28","cited_by_count":3,"area":null},{"id":"2205.06720","title":"On the Importance of Architecture and Feature Selection in Differentially Private Machine Learning","created":"2022-05-13","cited_by_count":3,"area":null},{"id":"2304.04164","title":"Gradient Sparsification for Efficient Wireless Federated Learning with Differential Privacy","created":"2023-04-09","cited_by_count":3,"area":null},{"id":"2306.11754","title":"Pre-Pruning and Gradient-Dropping Improve Differentially Private Image Classification","created":"2023-06-19","cited_by_count":3,"area":null},{"id":"2309.11516","title":"Private Matrix Factorization with Public Item Features","created":"2023-09-17","cited_by_count":3,"area":null},{"id":"2310.01304","title":"Coupling public and private gradient provably helps optimization","created":"2023-10-02","cited_by_count":3,"area":null},{"id":"2503.06009","title":"Nearly Optimal Differentially Private ReLU Regression","created":"2025-03-08","cited_by_count":3,"area":null},{"id":"2102.13522","title":"Experiments with Rich Regime Training for Deep Learning","created":"2021-02-26","cited_by_count":2,"area":null},{"id":"2403.13041","title":"Provable Privacy with Non-Private Pre-Processing","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2404.10881","title":"Differentially Private Optimization with Sparse Gradients","created":"2024-04-16","cited_by_count":2,"area":null},{"id":"2405.08043","title":"HRNet: Differentially Private Hierarchical and Multi-Resolution Network for Human Mobility Data Synthesization","created":"2024-05-13","cited_by_count":2,"area":null},{"id":"2505.21382","title":"DeCAF: Decentralized Consensus-And-Factorization for Low-Rank Adaptation of Foundation Models","created":"2025-05-27","cited_by_count":2,"area":"mllm"},{"id":"2506.15588","title":"Memory-Efficient Differentially Private Training with Gradient Random Projection","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2511.10859","title":"Private Zeroth-Order Optimization with Public Data","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2605.12994","title":"DP-Muon: Differentially Private Optimization via Matrix-Orthogonalized Momentum","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2103.00075","title":"Noisy Truncated SGD: Optimization and Generalization","created":"2021-02-26","cited_by_count":1,"area":null},{"id":"2211.07218","title":"SA-DPSGD: Differentially Private Stochastic Gradient Descent based on Simulated Annealing","created":"2022-11-14","cited_by_count":1,"area":null},{"id":"2311.06839","title":"Inference and Interference: The Role of Clipping, Pruning and Loss Landscapes in Differentially Private Stochastic Gradient Descent","created":"2023-11-12","cited_by_count":1,"area":null},{"id":"2402.06465","title":"On Differentially Private Subspace Estimation in a Distribution-Free Setting","created":"2024-02-09","cited_by_count":1,"area":null},{"id":"2504.10190","title":"Differentially Private 2D Human Pose Estimation","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2505.13655","title":"Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacy","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.15013","title":"Convergence of Adam in Deep ReLU Networks via Directional Complexity and Kakeya Bounds","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2507.06525","title":"AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2510.05416","title":"Correlating Cross-Iteration Noise for DP-SGD using Model Curvature","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2603.26227","title":"Privacy-Accuracy Trade-offs in High-Dimensional LASSO under Perturbation Mechanisms","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2407.15414","title":"Weights Shuffling for Improving DPSGD in Transformer-based Models","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2508.15523","title":"Stabilization of Perturbed Loss Function: Differential Privacy without Gradient Noise","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2605.03945","title":"Integrating Feature Correlation in Differential Privacy with Applications in DP-ERM","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2606.04375","title":"When Do Fewer Coordinates Suffice in DP-SGD?","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.26772","title":"Escaping Iterative Parameter-Space Noise: Differentially Private Learning with a Hypernetwork","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.21417","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2610.02943","title":"Kinematics-Induced Multimodal 3D Human Pose Estimation with Subject-Level Privacy","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}