{"total":168,"rows":[{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387,"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":"2201.12328","title":"Toward Training at ImageNet Scale with Differential Privacy","created":"2022-01-28","cited_by_count":87,"area":null},{"id":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84,"area":null},{"id":"2102.11845","title":"Learning with User-Level Privacy","created":"2021-02-23","cited_by_count":72,"area":null},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2209.14863","title":"Neural Networks Efficiently Learn Low-Dimensional Representations with SGD","created":"2022-09-29","cited_by_count":63,"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":"2207.00160","title":"When Does Differentially Private Learning Not Suffer in High Dimensions?","created":"2022-07-01","cited_by_count":48,"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":"2103.12024","title":"Stability and Deviation Optimal Risk Bounds with Convergence Rate $O(1/n)$","created":"2021-03-22","cited_by_count":42,"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":"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":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39,"area":null},{"id":"2102.01117","title":"SGD Generalizes Better Than GD (And Regularization Doesn't Help)","created":"2021-02-01","cited_by_count":38,"area":null},{"id":"2206.05187","title":"On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond","created":"2022-06-10","cited_by_count":38,"area":null},{"id":"2206.12680","title":"Topology-aware Generalization of Decentralized SGD","created":"2022-06-25","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":"2105.03793","title":"Stability and Generalization of Stochastic Gradient Methods for Minimax Problems","created":"2021-05-08","cited_by_count":36,"area":null},{"id":"2305.20057","title":"Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance","created":"2023-05-31","cited_by_count":36,"area":null},{"id":"2102.05274","title":"Stability of SGD: Tightness Analysis and Improved Bounds","created":"2021-02-10","cited_by_count":33,"area":null},{"id":"2110.03128","title":"On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications","created":"2021-10-07","cited_by_count":31,"area":null},{"id":"2210.00960","title":"Stability Analysis and Generalization Bounds of Adversarial Training","created":"2022-10-03","cited_by_count":30,"area":null},{"id":"2202.13441","title":"Stability vs Implicit Bias of Gradient Methods on Separable Data and Beyond","created":"2022-02-27","cited_by_count":29,"area":null},{"id":"2111.12876","title":"Time-independent Generalization Bounds for SGLD in Non-convex Settings","created":"2021-11-25","cited_by_count":27,"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":"2206.07082","title":"Stability and Generalization of Stochastic Optimization with Nonconvex and Nonsmooth Problems","created":"2022-06-14","cited_by_count":25,"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":"2107.05074","title":"SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs","created":"2021-07-11","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":"2202.04598","title":"Reproducibility in Optimization: Theoretical Framework and Limits","created":"2022-02-09","cited_by_count":21,"area":null},{"id":"2209.09298","title":"Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks","created":"2022-09-19","cited_by_count":21,"area":null},{"id":"2302.09235","title":"Generalization and Stability of Interpolating Neural Networks with Minimal Width","created":"2023-02-18","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":"2111.12050","title":"Simple Stochastic and Online Gradient Descent Algorithms for Pairwise Learning","created":"2021-11-23","cited_by_count":20,"area":null},{"id":"2205.13532","title":"Selective Prediction via Training Dynamics","created":"2022-05-26","cited_by_count":20,"area":null},{"id":"2112.10224","title":"Stable Conformal Prediction Sets","created":"2021-12-19","cited_by_count":19,"area":null},{"id":"2202.13361","title":"Benign Underfitting of Stochastic Gradient Descent","created":"2022-02-27","cited_by_count":19,"area":null},{"id":"2204.12446","title":"Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD","created":"2022-04-26","cited_by_count":19,"area":null},{"id":"2212.13556","title":"Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization","created":"2022-12-27","cited_by_count":19,"area":null},{"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":"2205.03014","title":"Differentially Private Generalized Linear Models Revisited","created":"2022-05-06","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":"2302.04925","title":"Information Theoretic Lower Bounds for Information Theoretic Upper Bounds","created":"2023-02-09","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":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15,"area":null},{"id":"2107.00469","title":"Never Go Full Batch (in Stochastic Convex Optimization)","created":"2021-06-29","cited_by_count":14,"area":null},{"id":"2206.03299","title":"Generalization Error Bounds for Deep Neural Networks Trained by SGD","created":"2022-06-07","cited_by_count":14,"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":"2402.09327","title":"Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization","created":"2024-02-14","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":"2206.01274","title":"Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares","created":"2022-06-02","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":"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":"2209.08951","title":"Generalization Bounds for Stochastic Gradient Descent via Localized $\\varepsilon$-Covers","created":"2022-09-19","cited_by_count":11,"area":null},{"id":"2211.10691","title":"Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2106.03034","title":"Minibatch and Momentum Model-based Methods for Stochastic Weakly Convex Optimization","created":"2021-06-06","cited_by_count":10,"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":"2306.02939","title":"Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm","created":"2023-06-05","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":"2106.15207","title":"Optimal Rates for Random Order Online Optimization","created":"2021-06-29","cited_by_count":9,"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":"2303.05369","title":"Data-dependent Generalization Bounds via Variable-Size Compressibility","created":"2023-03-09","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":"2203.03159","title":"Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime","created":"2022-03-07","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":"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":"2202.13328","title":"Thinking Outside the Ball: Optimal Learning with Gradient Descent for Generalized Linear Stochastic Convex Optimization","created":"2022-02-27","cited_by_count":7,"area":null},{"id":"2205.14278","title":"Generalization Bounds of Nonconvex-(Strongly)-Concave Stochastic Minimax Optimization","created":"2022-05-28","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":"2305.14683","title":"On progressive sharpening, flat minima and generalisation","created":"2023-05-24","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":"2305.12056","title":"Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent","created":"2023-05-20","cited_by_count":6,"area":null},{"id":"2310.20102","title":"Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds","created":"2023-10-31","cited_by_count":6,"area":null},{"id":"2404.04931","title":"The Sample Complexity of Gradient Descent in Stochastic Convex Optimization","created":"2024-04-07","cited_by_count":6,"area":null},{"id":"2106.06153","title":"Towards Understanding Generalization via Decomposing Excess Risk Dynamics","created":"2021-06-11","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":"2210.06593","title":"Differentially Private Online-to-Batch for Smooth Losses","created":"2022-10-12","cited_by_count":5,"area":null},{"id":"2304.12579","title":"Learning Trajectories are Generalization Indicators","created":"2023-04-25","cited_by_count":5,"area":null},{"id":"2305.01143","title":"Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Renyi's Entropy Perspective","created":"2023-05-02","cited_by_count":5,"area":null},{"id":"2305.02247","title":"Select without Fear: Almost All Mini-Batch Schedules Generalize Optimally","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2307.13680","title":"High Probability Analysis for Non-Convex Stochastic Optimization with Clipping","created":"2023-07-25","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":"2310.05696","title":"Little is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised Learning","created":"2023-10-09","cited_by_count":5,"area":null},{"id":"2404.08980","title":"Stability and Generalization in Free Adversarial Training","created":"2024-04-13","cited_by_count":5,"area":null},{"id":"2108.07414","title":"Stability and Generalization for Randomized Coordinate Descent","created":"2021-08-17","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":"2301.03125","title":"Sharper Analysis for Minibatch Stochastic Proximal Point Methods: Stability, Smoothness, and Deviation","created":"2023-01-09","cited_by_count":4,"area":null},{"id":"2401.03156","title":"Data-Dependent Stability Analysis of Adversarial Training","created":"2024-01-06","cited_by_count":4,"area":null},{"id":"2511.22270","title":"Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNs","created":"2025-11-27","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":"2202.06054","title":"Towards Data-Algorithm Dependent Generalization: a Case Study on Overparameterized Linear Regression","created":"2022-02-12","cited_by_count":3,"area":null}],"next_cursor":"100"}