{"total":186,"rows":[{"id":"2103.03279","title":"Remember What You Want to Forget: Algorithms for Machine Unlearning","created":"2021-03-04","cited_by_count":371,"area":"safety"},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2103.00039","title":"Practical and Private (Deep) Learning without Sampling or Shuffling","created":"2021-02-26","cited_by_count":170,"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":"2102.13179","title":"Machine Unlearning via Algorithmic Stability","created":"2021-02-25","cited_by_count":130,"area":"safety"},{"id":"2102.06062","title":"Deep Learning with Label Differential Privacy","created":"2021-02-11","cited_by_count":117,"area":null},{"id":"2201.12328","title":"Toward Training at ImageNet Scale with Differential Privacy","created":"2022-01-28","cited_by_count":87,"area":null},{"id":"2103.01516","title":"Private Stochastic Convex Optimization: Optimal Rates in $\\ell_1$ Geometry","created":"2021-03-02","cited_by_count":83,"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":"2102.03448","title":"Federated Reconstruction: Partially Local Federated Learning","created":"2021-02-05","cited_by_count":79,"area":null},{"id":"2102.11845","title":"Learning with User-Level Privacy","created":"2021-02-23","cited_by_count":72,"area":null},{"id":"2205.13710","title":"Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss","created":"2022-05-27","cited_by_count":61,"area":null},{"id":"2103.01278","title":"Non-Euclidean Differentially Private Stochastic Convex Optimization: Optimal Rates in Linear Time","created":"2021-03-01","cited_by_count":51,"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":"2203.00263","title":"Private Convex Optimization via Exponential Mechanism","created":"2022-03-01","cited_by_count":49,"area":null},{"id":"2306.08153","title":"(Amplified) Banded Matrix Factorization: A unified approach to private training","created":"2023-06-13","cited_by_count":49,"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":"2207.00160","title":"When Does Differentially Private Learning Not Suffer in High Dimensions?","created":"2022-07-01","cited_by_count":48,"area":null},{"id":"2106.01336","title":"Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data","created":"2021-06-02","cited_by_count":47,"area":null},{"id":"2106.13756","title":"Private Adaptive Gradient Methods for Convex Optimization","created":"2021-06-25","cited_by_count":46,"area":null},{"id":"2107.05585","title":"Differentially Private Stochastic Optimization: New Results in Convex and Non-Convex Settings","created":"2021-07-12","cited_by_count":45,"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":"2209.12269","title":"Algorithms that Approximate Data Removal: New Results and Limitations","created":"2022-09-25","cited_by_count":40,"area":"safety"},{"id":"2302.09483","title":"Why Is Public Pretraining Necessary for Private Model Training?","created":"2023-02-19","cited_by_count":37,"area":null},{"id":"2102.03832","title":"Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks","created":"2021-02-07","cited_by_count":36,"area":null},{"id":"2206.00846","title":"Faster Rates of Convergence to Stationary Points in Differentially Private Optimization","created":"2022-06-02","cited_by_count":32,"area":null},{"id":"2106.09779","title":"Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses","created":"2021-06-17","cited_by_count":30,"area":null},{"id":"2312.10336","title":"Certified Minimax Unlearning with Generalization Rates and Deletion Capacity","created":"2023-12-16","cited_by_count":29,"area":"safety"},{"id":"2103.11003","title":"Differentially private inference via noisy optimization","created":"2021-03-19","cited_by_count":27,"area":null},{"id":"2212.03714","title":"Reconstructing Training Data from Model Gradient, Provably","created":"2022-12-07","cited_by_count":27,"area":null},{"id":"2203.06735","title":"Private Non-Convex Federated Learning Without a Trusted Server","created":"2022-03-13","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":"2106.09481","title":"Stochastic Bias-Reduced Gradient Methods","created":"2021-06-17","cited_by_count":25,"area":null},{"id":"2205.13709","title":"DP-PCA: Statistically Optimal and Differentially Private PCA","created":"2022-05-27","cited_by_count":24,"area":null},{"id":"2201.09046","title":"Differentially Private SGDA for Minimax Problems","created":"2022-01-22","cited_by_count":23,"area":null},{"id":"2101.08925","title":"Differentially Private SGD with Non-Smooth Losses","created":"2021-01-22","cited_by_count":22,"area":null},{"id":"2206.00363","title":"Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization","created":"2022-06-01","cited_by_count":22,"area":null},{"id":"2103.15352","title":"Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps","created":"2021-03-29","cited_by_count":21,"area":null},{"id":"2303.07152","title":"Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning","created":"2023-03-13","cited_by_count":21,"area":null},{"id":"2108.02391","title":"Adapting to Function Difficulty and Growth Conditions in Private Optimization","created":"2021-08-05","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":"2208.07353","title":"Easy Differentially Private Linear Regression","created":"2022-08-15","cited_by_count":19,"area":null},{"id":"2302.01463","title":"Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy","created":"2023-02-02","cited_by_count":18,"area":null},{"id":"2309.00886","title":"Tight Bounds for Machine Unlearning via Differential Privacy","created":"2023-09-02","cited_by_count":18,"area":"safety"},{"id":"2104.02988","title":"Optimal Algorithms for Differentially Private Stochastic Monotone Variational Inequalities and Saddle-Point Problems","created":"2021-04-07","cited_by_count":17,"area":null},{"id":"2106.09805","title":"Shuffle Private Stochastic Convex Optimization","created":"2021-06-17","cited_by_count":17,"area":null},{"id":"2205.03014","title":"Differentially Private Generalized Linear Models Revisited","created":"2022-05-06","cited_by_count":17,"area":null},{"id":"2210.13537","title":"Private Online Prediction from Experts: Separations and Faster Rates","created":"2022-10-24","cited_by_count":17,"area":null},{"id":"2301.00457","title":"ReSQueing Parallel and Private Stochastic Convex Optimization","created":"2023-01-01","cited_by_count":17,"area":null},{"id":"2310.06289","title":"Better and Simpler Lower Bounds for Differentially Private Statistical Estimation","created":"2023-10-10","cited_by_count":17,"area":null},{"id":"2102.02167","title":"Algorithmic Instabilities of Accelerated Gradient Descent","created":"2021-02-03","cited_by_count":16,"area":null},{"id":"2210.08781","title":"Stochastic Differentially Private and Fair Learning","created":"2022-10-17","cited_by_count":16,"area":null},{"id":"2209.08005","title":"Stability and Generalization for Markov Chain Stochastic Gradient Methods","created":"2022-09-16","cited_by_count":14,"area":null},{"id":"2207.08347","title":"Private Convex Optimization in General Norms","created":"2022-07-18","cited_by_count":13,"area":null},{"id":"2305.13209","title":"Faster Differentially Private Convex Optimization via Second-Order Methods","created":"2023-05-22","cited_by_count":13,"area":null},{"id":"2403.00278","title":"Shifted Interpolation for Differential Privacy","created":"2024-03-01","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":"2205.09494","title":"Differentially private Riemannian optimization","created":"2022-05-19","cited_by_count":12,"area":null},{"id":"2302.09699","title":"Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks","created":"2023-02-20","cited_by_count":12,"area":null},{"id":"2302.12909","title":"Differentially Private Algorithms for the Stochastic Saddle Point Problem with Optimal Rates for the Strong Gap","created":"2023-02-24","cited_by_count":12,"area":null},{"id":"2310.19733","title":"Differentially Private Reward Estimation with Preference Feedback","created":"2023-10-30","cited_by_count":12,"area":"alignment"},{"id":"2311.03797","title":"User-level Differentially Private Stochastic Convex Optimization: Efficient Algorithms with Optimal Rates","created":"2023-11-07","cited_by_count":12,"area":null},{"id":"2405.13453","title":"A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy","created":"2024-05-22","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":"2202.11199","title":"Differentially Private Regression with Unbounded Covariates","created":"2022-02-19","cited_by_count":10,"area":null},{"id":"2210.06328","title":"Momentum Aggregation for Private Non-convex ERM","created":"2022-10-12","cited_by_count":10,"area":null},{"id":"2302.03884","title":"DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning","created":"2023-02-08","cited_by_count":10,"area":null},{"id":"2302.06085","title":"Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler","created":"2023-02-13","cited_by_count":10,"area":null},{"id":"2310.20579","title":"Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks","created":"2023-10-31","cited_by_count":10,"area":null},{"id":"2402.11173","title":"How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization","created":"2024-02-17","cited_by_count":10,"area":null},{"id":"2206.01836","title":"Dimension Independent Generalization of DP-SGD for Overparameterized Smooth Convex Optimization","created":"2022-06-03","cited_by_count":9,"area":null},{"id":"2301.13273","title":"Near Optimal Private and Robust Linear Regression","created":"2023-01-30","cited_by_count":9,"area":null},{"id":"2402.19437","title":"Differentially Private Worst-group Risk Minimization","created":"2024-02-29","cited_by_count":9,"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":"2201.03204","title":"Differentially Private $\\ell_1$-norm Linear Regression with Heavy-tailed Data","created":"2022-01-10","cited_by_count":8,"area":null},{"id":"2207.05827","title":"Differentially Private Linear Bandits with Partial Distributed Feedback","created":"2022-07-12","cited_by_count":8,"area":null},{"id":"2207.08257","title":"Uniform Stability for First-Order Empirical Risk Minimization","created":"2022-07-17","cited_by_count":8,"area":null},{"id":"2303.18047","title":"Differentially Private Stochastic Convex Optimization in (Non)-Euclidean Space Revisited","created":"2023-03-31","cited_by_count":8,"area":null},{"id":"2305.04912","title":"On User-Level Private Convex Optimization","created":"2023-05-08","cited_by_count":8,"area":null},{"id":"2405.08920","title":"Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning","created":"2024-05-14","cited_by_count":8,"area":null},{"id":"2406.19579","title":"Private Zeroth-Order Nonsmooth Nonconvex Optimization","created":"2024-06-27","cited_by_count":8,"area":null},{"id":"2407.09690","title":"Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses","created":"2024-07-12","cited_by_count":8,"area":null},{"id":"2204.10376","title":"Differentially Private Learning with Margin Guarantees","created":"2022-04-21","cited_by_count":7,"area":null},{"id":"2211.13403","title":"Differentially Private Image Classification from Features","created":"2022-11-24","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":"2403.02912","title":"Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2207.04686","title":"(Nearly) Optimal Private Linear Regression via Adaptive Clipping","created":"2022-07-11","cited_by_count":6,"area":null},{"id":"2303.10758","title":"Lower Generalization Bounds for GD and SGD in Smooth Stochastic Convex Optimization","created":"2023-03-19","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":"2406.02789","title":"Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions","created":"2024-06-04","cited_by_count":6,"area":null},{"id":"2101.07413","title":"Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent","created":"2021-01-19","cited_by_count":5,"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":"2210.06593","title":"Differentially Private Online-to-Batch for Smooth Losses","created":"2022-10-12","cited_by_count":5,"area":null},{"id":"2307.10999","title":"Private Federated Learning with Autotuned Compression","created":"2023-07-20","cited_by_count":5,"area":null},{"id":"2310.01139","title":"Minibatch and Local SGD: Algorithmic Stability and Linear Speedup in Generalization","created":"2023-10-02","cited_by_count":5,"area":null},{"id":"2405.15979","title":"BadGD: A unified data-centric framework to identify gradient descent vulnerabilities","created":"2024-05-24","cited_by_count":5,"area":"safety"},{"id":"2503.18317","title":"Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization","created":"2025-03-24","cited_by_count":5,"area":null},{"id":"2102.05134","title":"Local and Global Uniform Convexity Conditions","created":"2021-02-09","cited_by_count":4,"area":null},{"id":"2203.09276","title":"Stochastic and Private Nonconvex Outlier-Robust PCA","created":"2022-03-17","cited_by_count":4,"area":null},{"id":"2206.03617","title":"Subject Granular Differential Privacy in Federated Learning","created":"2022-06-07","cited_by_count":4,"area":null}],"next_cursor":"100"}