{"total":82,"rows":[{"id":"2202.06526","title":"Benign Overfitting in Two-layer Convolutional Neural Networks","created":"2022-02-14","cited_by_count":91,"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":"2303.04145","title":"Benign Overfitting for Two-layer ReLU Convolutional Neural Networks","created":"2023-03-07","cited_by_count":34,"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":"2109.14509","title":"PAC-Bayes Information Bottleneck","created":"2021-09-29","cited_by_count":28,"area":null},{"id":"2108.00781","title":"Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers","created":"2021-08-02","cited_by_count":27,"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":"2306.03824","title":"Understanding Generalization of Federated Learning via Stability: Heterogeneity Matters","created":"2023-06-06","cited_by_count":27,"area":null},{"id":"2304.09595","title":"AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNs","created":"2023-04-19","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":"2308.16375","title":"A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications","created":"2023-08-31","cited_by_count":22,"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":"2101.04968","title":"Learning with Gradient Descent and Weakly Convex Losses","created":"2021-01-13","cited_by_count":16,"area":null},{"id":"2102.02976","title":"Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise Channels","created":"2021-02-05","cited_by_count":15,"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":"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":"2311.01046","title":"Time-Independent Information-Theoretic Generalization Bounds for SGLD","created":"2023-11-02","cited_by_count":12,"area":null},{"id":"2402.03990","title":"Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2405.15709","title":"Information-theoretic Generalization Analysis for Expected Calibration Error","created":"2024-05-24","cited_by_count":10,"area":null},{"id":"2209.02525","title":"Generalisation under gradient descent via deterministic PAC-Bayes","created":"2022-09-06","cited_by_count":9,"area":null},{"id":"2305.16891","title":"Generalization Guarantees of Gradient Descent for Multi-Layer Neural Networks","created":"2023-05-26","cited_by_count":9,"area":null},{"id":"2404.17442","title":"Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets","created":"2024-04-26","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":"2201.06656","title":"Generalization in Supervised Learning Through Riemannian Contraction","created":"2022-01-17","cited_by_count":8,"area":null},{"id":"2209.13262","title":"Exploring the Algorithm-Dependent Generalization of AUPRC Optimization with List Stability","created":"2022-09-27","cited_by_count":8,"area":null},{"id":"2507.03756","title":"Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation Analysis","created":"2025-07-04","cited_by_count":7,"area":"diffusion"},{"id":"2206.07892","title":"Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence","created":"2022-06-16","cited_by_count":6,"area":null},{"id":"2210.06143","title":"On the Importance of Gradient Norm in PAC-Bayesian Bounds","created":"2022-10-12","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":"2106.06153","title":"Towards Understanding Generalization via Decomposing Excess Risk Dynamics","created":"2021-06-11","cited_by_count":5,"area":null},{"id":"2201.04545","title":"On generalization bounds for deep networks based on loss surface implicit regularization","created":"2022-01-12","cited_by_count":5,"area":null},{"id":"2205.13799","title":"Generalization Bounds for Gradient Methods via Discrete and Continuous Prior","created":"2022-05-27","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":"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":"2506.03849","title":"Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models","created":"2025-06-04","cited_by_count":5,"area":"diffusion"},{"id":"2207.09304","title":"A sharp uniform-in-time error estimate for Stochastic Gradient Langevin Dynamics","created":"2022-07-19","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":"2409.19431","title":"Generalization and Robustness of the Tilted Empirical Risk","created":"2024-09-28","cited_by_count":4,"area":null},{"id":"2104.05600","title":"PAC Bayesian Performance Guarantees for Deep (Stochastic) Networks in Medical Imaging","created":"2021-04-12","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},{"id":"2311.00274","title":"Generalization Bounds for Label Noise Stochastic Gradient Descent","created":"2023-11-01","cited_by_count":3,"area":null},{"id":"2502.17024","title":"Towards Auto-Regressive Next-Token Prediction: In-Context Learning Emerges from Generalization","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2202.09052","title":"Tackling benign nonconvexity with smoothing and stochastic gradients","created":"2022-02-18","cited_by_count":2,"area":null},{"id":"2205.11970","title":"Weak Convergence of Approximate reflection coupling and its Application to Non-convex Optimization","created":"2022-05-24","cited_by_count":2,"area":null},{"id":"2311.04561","title":"Information-Theoretic Generalization Bounds for Transductive Learning and its Applications","created":"2023-11-08","cited_by_count":2,"area":null},{"id":"2311.08745","title":"Using Stochastic Gradient Descent to Smooth Nonconvex Functions: Analysis of Implicit Graduated Optimization","created":"2023-11-15","cited_by_count":2,"area":null},{"id":"2402.05101","title":"Tighter Generalisation Bounds via Interpolation","created":"2024-02-07","cited_by_count":2,"area":null},{"id":"2502.07584","title":"Generalization Bounds for Markov Algorithms through Entropy Flow Computations","created":"2025-02-11","cited_by_count":2,"area":null},{"id":"2502.12508","title":"Understanding Generalization in Transformers: Error Bounds and Training Dynamics Under Benign and Harmful Overfitting","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2505.19087","title":"Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes","created":"2025-05-25","cited_by_count":2,"area":null},{"id":"2510.08852","title":"On the Alignment Between Supervised and Self-Supervised Contrastive Learning","created":"2025-10-09","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":"2112.08439","title":"Generalization Bounds for Stochastic Gradient Langevin Dynamics: A Unified View via Information Leakage Analysis","created":"2021-12-14","cited_by_count":1,"area":null},{"id":"2202.06880","title":"Black-Box Generalization: Stability of Zeroth-Order Learning","created":"2022-02-14","cited_by_count":1,"area":null},{"id":"2208.14092","title":"Super-model ecosystem: A domain-adaptation perspective","created":"2022-08-30","cited_by_count":1,"area":null},{"id":"2211.03570","title":"Do highly over-parameterized neural networks generalize since bad solutions are rare?","created":"2022-11-07","cited_by_count":1,"area":null},{"id":"2301.06769","title":"Geometric ergodicity of SGLD via reflection coupling","created":"2023-01-17","cited_by_count":1,"area":null},{"id":"2409.01498","title":"A practical generalization metric for deep networks benchmarking","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2504.02957","title":"Randomized Pairwise Learning with Adaptive Sampling: A PAC-Bayes Analysis","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2510.06028","title":"Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime","created":"2025-10-07","cited_by_count":1,"area":null},{"id":"2102.01302","title":"Stability and Generalization of the Decentralized Stochastic Gradient Descent","created":"2021-02-02","cited_by_count":0,"area":null},{"id":"2103.01887","title":"Self-Regularity of Non-Negative Output Weights for Overparameterized Two-Layer Neural Networks","created":"2021-03-02","cited_by_count":0,"area":null},{"id":"2110.13750","title":"Optimizing Information-theoretical Generalization Bounds via Anisotropic Noise in SGLD","created":"2021-10-26","cited_by_count":0,"area":null},{"id":"2205.12959","title":"Uniform Generalization Bound on Time and Inverse Temperature for Gradient Descent Algorithm and its Application to Analysis of Simulated Annealing","created":"2022-05-25","cited_by_count":0,"area":null},{"id":"2305.18864","title":"Stochastic Gradient Langevin Dynamics Based on Quantization with Increasing Resolution","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2306.09624","title":"Power-law Dynamic arising from machine learning","created":"2023-06-16","cited_by_count":0,"area":null},{"id":"2308.09430","title":"Towards Understanding the Generalizability of Delayed Stochastic Gradient Descent","created":"2023-08-18","cited_by_count":0,"area":null},{"id":"2312.02182","title":"Adam-like Algorithm with Smooth Clipping Attains Global Minima: Analysis Based on Ergodicity of Functional SDEs","created":"2023-11-29","cited_by_count":0,"area":null},{"id":"2410.16868","title":"Rethinking generalization of classifiers in separable classes scenarios and over-parameterized regimes","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2505.19470","title":"Information-theoretic Generalization Analysis for VQ-VAEs: A Role of Latent Variables","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2506.10664","title":"Sequential Off-Policy Learning with Logarithmic Smoothing","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2506.11357","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2506.18645","title":"Tight Generalization Error Bounds for Stochastic Gradient Descent in Non-convex Learning","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2511.12188","title":"Scaling Law Analysis in Federated Learning: How to Select the Optimal Model Size?","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2602.04107","title":"Supervised Learning as Lossy Compression: Characterizing Generalization and Sample Complexity via Finite Blocklength Analysis","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.05333","title":"Pool-based Active Learning as Noisy Lossy Compression: Characterizing Label Complexity via Finite Blocklength Analysis","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.22936","title":"Generalization Bounds of Stochastic Gradient Descent in Homogeneous Neural Networks","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2604.06281","title":"Generalization error bounds for two-layer neural networks with Lipschitz loss function","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2605.28513","title":"Learning Theory of the SVRG: Generalization and Convergence Analysis","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.04442","title":"Tightening the Score Matching Gap for Diffusion Models","created":"2026-07-05","cited_by_count":0,"area":"diffusion"},{"id":"2608.30431","title":"Generalization as a robust performance property of learning-enabled dynamical systems","created":"2026-08-31","cited_by_count":0,"area":null}],"next_cursor":null}