{"total":139,"rows":[{"id":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224,"area":null},{"id":"2303.00654","title":"How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy","created":"2023-03-01","cited_by_count":153,"area":null},{"id":"2206.07136","title":"Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger","created":"2022-06-14","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":"2305.01588","title":"Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees","created":"2023-05-02","cited_by_count":83,"area":null},{"id":"2204.00401","title":"CTAB-GAN+: Enhancing Tabular Data Synthesis","created":"2022-04-01","cited_by_count":70,"area":null},{"id":"2106.13673","title":"Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy","created":"2021-06-25","cited_by_count":69,"area":null},{"id":"2110.14216","title":"What Do We Mean by Generalization in Federated Learning?","created":"2021-10-27","cited_by_count":62,"area":null},{"id":"2203.11481","title":"Mixed Differential Privacy in Computer Vision","created":"2022-03-22","cited_by_count":54,"area":null},{"id":"2109.11429","title":"Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data","created":"2021-09-23","cited_by_count":48,"area":null},{"id":"2203.05363","title":"Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)","created":"2022-03-10","cited_by_count":48,"area":null},{"id":"2401.04343","title":"Private Fine-tuning of Large Language Models with Zeroth-order Optimization","created":"2024-01-09","cited_by_count":41,"area":null},{"id":"2106.07830","title":"On the Convergence and Calibration of Deep Learning with Differential Privacy","created":"2021-06-15","cited_by_count":36,"area":null},{"id":"2206.13033","title":"Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization","created":"2022-06-27","cited_by_count":36,"area":null},{"id":"2103.11109","title":"DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2206.07737","title":"Disparate Impact in Differential Privacy from Gradient Misalignment","created":"2022-06-15","cited_by_count":31,"area":null},{"id":"2111.00173","title":"Dynamic Differential-Privacy Preserving SGD","created":"2021-10-30","cited_by_count":30,"area":null},{"id":"2212.13185","title":"Generalized Differentiable RANSAC","created":"2022-12-26","cited_by_count":30,"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":"2202.00980","title":"Robust Training of Neural Networks Using Scale Invariant Architectures","created":"2022-02-02","cited_by_count":29,"area":null},{"id":"2107.14586","title":"An Efficient DP-SGD Mechanism for Large Scale NLP Models","created":"2021-07-14","cited_by_count":27,"area":null},{"id":"2112.02548","title":"Generative Modeling of Turbulence","created":"2021-12-05","cited_by_count":26,"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":"2202.11632","title":"Mirror Descent Strikes Again: Optimal Stochastic Convex Optimization under Infinite Noise Variance","created":"2022-02-23","cited_by_count":24,"area":null},{"id":"2202.05318","title":"Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning","created":"2022-02-10","cited_by_count":23,"area":null},{"id":"2406.15244","title":"AdaGrad under Anisotropic Smoothness","created":"2024-06-21","cited_by_count":22,"area":null},{"id":"2206.02617","title":"Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent","created":"2022-06-06","cited_by_count":20,"area":null},{"id":"2206.10713","title":"Beyond Uniform Lipschitz Condition in Differentially Private Optimization","created":"2022-06-21","cited_by_count":19,"area":null},{"id":"2205.03014","title":"Differentially Private Generalized Linear Models Revisited","created":"2022-05-06","cited_by_count":17,"area":null},{"id":"2302.02589","title":"$z$-SignFedAvg: A Unified Stochastic Sign-based Compression for Federated Learning","created":"2023-02-06","cited_by_count":17,"area":null},{"id":"2311.14632","title":"Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach","created":"2023-11-24","cited_by_count":14,"area":null},{"id":"2502.07923","title":"Sign Operator for Coping with Heavy-Tailed Noise in Non-Convex Optimization: High Probability Bounds Under $(L_0, L_1)$-Smoothness","created":"2025-02-11","cited_by_count":13,"area":null},{"id":"2309.16398","title":"Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey","created":"2023-09-28","cited_by_count":12,"area":null},{"id":"2305.16202","title":"DP-SGD Without Clipping: The Lipschitz Neural Network Way","created":"2023-05-25","cited_by_count":11,"area":null},{"id":"2305.18929","title":"Clip21: Error Feedback for Gradient Clipping","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2108.11483","title":"Heavy-tailed Streaming Statistical Estimation","created":"2021-08-25","cited_by_count":10,"area":null},{"id":"2111.13895","title":"Towards Understanding the Impact of Model Size on Differential Private Classification","created":"2021-11-27","cited_by_count":10,"area":null},{"id":"2210.00690","title":"Taming Fat-Tailed (\"Heavier-Tailed'' with Potentially Infinite Variance) Noise in Federated Learning","created":"2022-10-03","cited_by_count":10,"area":null},{"id":"2305.09896","title":"Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression","created":"2023-05-17","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":"2308.14606","title":"On the Tradeoff between Privacy Preservation and Byzantine-Robustness in Decentralized Learning","created":"2023-08-28","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":"2112.14430","title":"DP-FP: Differentially Private Forward Propagation for Large Models","created":"2021-12-29","cited_by_count":7,"area":null},{"id":"2306.08173","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2310.18784","title":"High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise","created":"2023-10-28","cited_by_count":7,"area":null},{"id":"2401.16687","title":"Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks","created":"2024-01-30","cited_by_count":7,"area":null},{"id":"2406.11733","title":"To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions","created":"2024-06-17","cited_by_count":7,"area":null},{"id":"2410.15637","title":"Large Deviation Upper Bounds and Improved MSE Rates of Nonlinear SGD: Heavy-tailed Noise and Power of Symmetry","created":"2024-10-21","cited_by_count":7,"area":null},{"id":"2502.04164","title":"Efficient Distributed Optimization under Heavy-Tailed Noise","created":"2025-02-06","cited_by_count":7,"area":null},{"id":"2306.08656","title":"Augment then Smooth: Reconciling Differential Privacy with Certified Robustness","created":"2023-06-14","cited_by_count":6,"area":null},{"id":"2503.22988","title":"DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation","created":"2025-03-29","cited_by_count":6,"area":null},{"id":"2106.07094","title":"On the Convergence of Differentially Private Federated Learning on Non-Lipschitz Objectives, and with Normalized Client Updates","created":"2021-06-13","cited_by_count":5,"area":null},{"id":"2110.07435","title":"Adaptive Differentially Private Empirical Risk Minimization","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2203.17028","title":"Differentially Private Federated Learning via Reconfigurable Intelligent Surface","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2303.06302","title":"Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Survey","created":"2023-03-11","cited_by_count":5,"area":null},{"id":"2404.10995","title":"Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Clipping Bias and Remedies","created":"2024-04-17","cited_by_count":5,"area":null},{"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":"2503.03486","title":"Differentially Private Learners for Heterogeneous Treatment Effects","created":"2025-03-05","cited_by_count":5,"area":null},{"id":"2107.04265","title":"Sensitivity analysis in differentially private machine learning using hybrid automatic differentiation","created":"2021-07-09","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":"2402.18905","title":"Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2405.02638","title":"PrivSGP-VR: Differentially Private Variance-Reduced Stochastic Gradient Push with Tight Utility Bounds","created":"2024-05-04","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":"2409.02404","title":"Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation","created":"2024-09-04","cited_by_count":4,"area":null},{"id":"2502.17772","title":"An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2202.13932","title":"Leveraging Channel Noise for Sampling and Privacy via Quantized Federated Langevin Monte Carlo","created":"2022-02-28","cited_by_count":3,"area":null},{"id":"2205.04095","title":"SmoothNets: Optimizing CNN architecture design for differentially private deep learning","created":"2022-05-09","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":"2209.07403","title":"Private Stochastic Optimization With Large Worst-Case Lipschitz Parameter","created":"2022-09-15","cited_by_count":3,"area":null},{"id":"2305.02942","title":"Incentivising the federation: gradient-based metrics for data selection and valuation in private decentralised training","created":"2023-05-04","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":"2401.17127","title":"Personalized Differential Privacy for Ridge Regression","created":"2024-01-30","cited_by_count":3,"area":null},{"id":"2403.02051","title":"Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping","created":"2024-03-04","cited_by_count":3,"area":null},{"id":"2412.01630","title":"Review of Mathematical Optimization in Federated Learning","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2502.13482","title":"Smoothed Normalization for Efficient Distributed Private Optimization","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2507.09093","title":"Sharp High-Probability Rates for Nonlinear SGD under Heavy-Tailed Noise via Symmetrization","created":"2025-07-12","cited_by_count":3,"area":null},{"id":"2107.04296","title":"Differentially private training of neural networks with Langevin dynamics for calibrated predictive uncertainty","created":"2021-07-09","cited_by_count":2,"area":null},{"id":"2206.07126","title":"Lazy Queries Can Reduce Variance in Zeroth-order Optimization","created":"2022-06-14","cited_by_count":2,"area":null},{"id":"2210.15961","title":"DPVIm: Differentially Private Variational Inference Improved","created":"2022-10-28","cited_by_count":2,"area":null},{"id":"2302.02971","title":"U-Clip: On-Average Unbiased Stochastic Gradient Clipping","created":"2023-02-06","cited_by_count":2,"area":null},{"id":"2302.09634","title":"Magnitude Matters: Fixing SIGNSGD Through Magnitude-Aware Sparsification in the Presence of Data Heterogeneity","created":"2023-02-19","cited_by_count":2,"area":null},{"id":"2302.14518","title":"Generalization Error Bounds for Noisy, Iterative Algorithms via Maximal Leakage","created":"2023-02-28","cited_by_count":2,"area":null},{"id":"2308.12018","title":"Bias-Aware Minimisation: Understanding and Mitigating Estimator Bias in Private SGD","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2310.00829","title":"Online Sensitivity Optimization in Differentially Private Learning","created":"2023-10-02","cited_by_count":2,"area":null},{"id":"2312.02074","title":"Federated Learning is Better with Non-Homomorphic Encryption","created":"2023-12-04","cited_by_count":2,"area":null},{"id":"2312.03792","title":"PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2402.08344","title":"Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training","created":"2024-02-13","cited_by_count":2,"area":null},{"id":"2507.20560","title":"Statistical Inference for Differentially Private Stochastic Gradient Descent","created":"2025-07-28","cited_by_count":2,"area":null},{"id":"2512.01025","title":"Operator-Theoretic Framework for Gradient-Free Federated Learning","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2603.03226","title":"Adaptive Methods Are Preferable in High Privacy Settings: An SDE Perspective","created":"2026-03-03","cited_by_count":2,"area":null},{"id":"2110.08851","title":"Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning","created":"2021-10-17","cited_by_count":1,"area":null},{"id":"2306.08280","title":"Differentially Private Wireless Federated Learning Using Orthogonal Sequences","created":"2023-06-14","cited_by_count":1,"area":null},{"id":"2306.14094","title":"Locally Differentially Private Distributed Online Learning with Guaranteed Optimality","created":"2023-06-25","cited_by_count":1,"area":null},{"id":"2308.10457","title":"ALI-DPFL: Differentially Private Federated Learning with Adaptive Local Iterations","created":"2023-08-21","cited_by_count":1,"area":null},{"id":"2308.15250","title":"The Relative Gaussian Mechanism and its Application to Private Gradient Descent","created":"2023-08-29","cited_by_count":1,"area":null},{"id":"2310.18001","title":"DP-SGD with weight clipping","created":"2023-10-27","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":"2410.06878","title":"Noise is All You Need: Private Second-Order Convergence of Noisy SGD","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2410.13954","title":"Nonlinear Stochastic Gradient Descent and Heavy-tailed Noise: A Unified Framework and High-probability Guarantees","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2411.03059","title":"Enhancing DP-SGD through Non-monotonous Adaptive Scaling Gradient Weight","created":"2024-11-05","cited_by_count":1,"area":null}],"next_cursor":"100"}