{"total":89,"rows":[{"id":"2210.16859","title":"A Solvable Model of Neural Scaling Laws","created":"2022-10-30","cited_by_count":116,"area":null},{"id":"2103.01550","title":"Label-Imbalanced and Group-Sensitive Classification under Overparameterization","created":"2021-03-02","cited_by_count":74,"area":null},{"id":"2401.15604","title":"Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization","created":"2024-01-28","cited_by_count":42,"area":"diffusion"},{"id":"2406.06213","title":"A Statistical Theory of Regularization-Based Continual Learning","created":"2024-06-10","cited_by_count":33,"area":null},{"id":"2108.05574","title":"Implicit Sparse Regularization: The Impact of Depth and Early Stopping","created":"2021-08-12","cited_by_count":30,"area":null},{"id":"2302.05933","title":"Generalization Ability of Wide Neural Networks on $\\mathbb{R}$","created":"2023-02-12","cited_by_count":30,"area":null},{"id":"2305.14077","title":"Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension","created":"2023-05-23","cited_by_count":26,"area":null},{"id":"2107.13289","title":"The loss landscape of deep linear neural networks: a second-order analysis","created":"2021-07-28","cited_by_count":24,"area":null},{"id":"2111.05326","title":"The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning","created":"2021-11-09","cited_by_count":23,"area":null},{"id":"2111.07167","title":"The Three Stages of Learning Dynamics in High-Dimensional Kernel Methods","created":"2021-11-13","cited_by_count":22,"area":null},{"id":"2106.15216","title":"A Non-parametric View of FedAvg and FedProx: Beyond Stationary Points","created":"2021-06-29","cited_by_count":13,"area":null},{"id":"2107.12972","title":"Channel-Wise Early Stopping without a Validation Set via NNK Polytope Interpolation","created":"2021-07-27","cited_by_count":11,"area":null},{"id":"2309.04268","title":"Optimal Rate of Kernel Regression in Large Dimensions","created":"2023-09-08","cited_by_count":11,"area":null},{"id":"2406.04425","title":"On Regularization via Early Stopping for Least Squares Regression","created":"2024-06-06","cited_by_count":11,"area":null},{"id":"2301.07605","title":"Strong inductive biases provably prevent harmless interpolation","created":"2023-01-18","cited_by_count":10,"area":null},{"id":"2202.11461","title":"Exponential Tail Local Rademacher Complexity Risk Bounds Without the Bernstein Condition","created":"2022-02-23","cited_by_count":9,"area":null},{"id":"2502.01347","title":"Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization","created":"2025-02-03","cited_by_count":9,"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":"2203.03791","title":"Data adaptive RKHS Tikhonov regularization for learning kernels in operators","created":"2022-03-08","cited_by_count":8,"area":null},{"id":"2209.03042","title":"Graph Neural Networks for Low-Energy Event Classification & Reconstruction in IceCube","created":"2022-09-07","cited_by_count":8,"area":null},{"id":"2409.09745","title":"The Optimality of (Accelerated) SGD for High-Dimensional Quadratic Optimization","created":"2024-09-15","cited_by_count":8,"area":null},{"id":"2109.13921","title":"Click-through Rate Prediction with Auto-Quantized Contrastive Learning","created":"2021-09-27","cited_by_count":7,"area":null},{"id":"2402.03839","title":"Random features models: a way to study the success of naive imputation","created":"2024-02-06","cited_by_count":7,"area":null},{"id":"2305.03531","title":"Random Smoothing Regularization in Kernel Gradient Descent Learning","created":"2023-05-05","cited_by_count":6,"area":null},{"id":"2310.01609","title":"Adversarial Contextual Bandits Go Kernelized","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2107.05341","title":"Nonparametric Regression with Shallow Overparameterized Neural Networks Trained by GD with Early Stopping","created":"2021-07-12","cited_by_count":5,"area":null},{"id":"2108.11872","title":"Comparing Classes of Estimators: When does Gradient Descent Beat Ridge Regression in Linear Models?","created":"2021-08-26","cited_by_count":5,"area":null},{"id":"2202.04146","title":"A Neural Phillips Curve and a Deep Output Gap","created":"2022-02-08","cited_by_count":5,"area":null},{"id":"2207.09097","title":"Lazy Estimation of Variable Importance for Large Neural Networks","created":"2022-07-19","cited_by_count":5,"area":null},{"id":"2212.13848","title":"Learning Lipschitz Functions by GD-trained Shallow Overparameterized ReLU Neural Networks","created":"2022-12-28","cited_by_count":5,"area":null},{"id":"2304.10060","title":"Optimality of Robust Online Learning","created":"2023-04-20","cited_by_count":5,"area":null},{"id":"2305.18506","title":"Generalization Ability of Wide Residual Networks","created":"2023-05-29","cited_by_count":5,"area":null},{"id":"2307.07002","title":"Classical Out-of-Distribution Detection Methods Benchmark in Text Classification Tasks","created":"2023-07-13","cited_by_count":5,"area":null},{"id":"2106.05397","title":"From inexact optimization to learning via gradient concentration","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2108.10764","title":"Regularizing Transformers With Deep Probabilistic Layers","created":"2021-08-23","cited_by_count":4,"area":null},{"id":"2210.00346","title":"Behind the Scenes of Gradient Descent: A Trajectory Analysis via Basis Function Decomposition","created":"2022-10-01","cited_by_count":4,"area":null},{"id":"2303.07537","title":"Fractional dynamics foster deep learning of COPD stage prediction","created":"2023-03-13","cited_by_count":4,"area":null},{"id":"2402.16793","title":"Failures and Successes of Cross-Validation for Early-Stopped Gradient Descent","created":"2024-02-26","cited_by_count":4,"area":null},{"id":"2502.06861","title":"Design Considerations in Offline Preference-based RL","created":"2025-02-08","cited_by_count":4,"area":"alignment"},{"id":"2505.22048","title":"Learning Curves of Stochastic Gradient Descent in Kernel Regression","created":"2025-05-28","cited_by_count":4,"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":"2304.13616","title":"CROP: Towards Distributional-Shift Robust Reinforcement Learning using Compact Reshaped Observation Processing","created":"2023-04-26","cited_by_count":3,"area":null},{"id":"2312.05885","title":"Adaptive Parameter Selection for Kernel Ridge Regression","created":"2023-12-10","cited_by_count":3,"area":null},{"id":"2412.01120","title":"Reliable and scalable variable importance estimation via warm-start and early stopping","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2509.05106","title":"Spectral Algorithms in Misspecified Regression: Convergence under Covariate Shift","created":"2025-09-05","cited_by_count":3,"area":null},{"id":"2308.08682","title":"Quantifying Overfitting: Introducing the Overfitting Index","created":"2023-08-16","cited_by_count":2,"area":null},{"id":"2309.04236","title":"Adaptive Distributed Kernel Ridge Regression: A Feasible Distributed Learning Scheme for Data Silos","created":"2023-09-08","cited_by_count":2,"area":null},{"id":"2311.16333","title":"From Reactive to Proactive Volatility Modeling with Hemisphere Neural Networks","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2404.17746","title":"On the Rashomon ratio of infinite hypothesis sets","created":"2024-04-27","cited_by_count":2,"area":null},{"id":"2409.00915","title":"On the Pinsker bound of inner product kernel regression in large dimensions","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2411.02904","title":"Gradient Descent Finds Over-Parameterized Neural Networks with Sharp Generalization for Nonparametric Regression","created":"2024-11-05","cited_by_count":2,"area":null},{"id":"2503.00504","title":"On the Saturation Effects of Spectral Algorithms in Large Dimensions","created":"2025-03-01","cited_by_count":2,"area":null},{"id":"2512.24999","title":"Basic Inequalities for First-Order Optimization with Applications to Statistical Risk Analysis","created":"2025-12-31","cited_by_count":2,"area":null},{"id":"2202.00420","title":"Iterative regularization for low complexity regularizers","created":"2022-02-01","cited_by_count":1,"area":null},{"id":"2211.11491","title":"Self-Adaptive, Dynamic, Integrated Statistical and Information Theory Learning","created":"2022-11-21","cited_by_count":1,"area":null},{"id":"2311.01762","title":"Changing the Kernel During Training Leads to Double Descent in Kernel Regression","created":"2023-11-03","cited_by_count":1,"area":null},{"id":"2402.12885","title":"A Bound on the Maximal Marginal Degrees of Freedom","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2507.11515","title":"AirLLM: Diffusion Policy-based Adaptive LoRA for Remote Fine-Tuning of LLM over the Air","created":"2025-07-15","cited_by_count":1,"area":"diffusion"},{"id":"2509.24991","title":"Sampling Complexity of TD and PPO in RKHS","created":"2025-09-29","cited_by_count":1,"area":"deeprl"},{"id":"2602.13942","title":"A Theoretical Framework for LLM Fine-tuning Using Early Stopping for Non-random Initialization","created":"2026-02-15","cited_by_count":1,"area":null},{"id":"2603.03401","title":"Beyond Cross-Validation: Adaptive Parameter Selection for Kernel-Based Gradient Descents","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2603.25466","title":"Residual-as-Teacher: Mitigating Bias Propagation in Student--Teacher Estimation","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2610.04756","title":"When Is Enough Enough in Self-Evolving LLM Systems?","created":"2026-10-03","cited_by_count":1,"area":"synth"},{"id":"2211.10061","title":"Data-Adaptive Discriminative Feature Localization with Statistically Guaranteed Interpretation","created":"2022-11-18","cited_by_count":0,"area":null},{"id":"2212.12675","title":"Iterative regularization in classification via hinge loss diagonal descent","created":"2022-12-24","cited_by_count":0,"area":null},{"id":"2309.16827","title":"Post-Training Overfitting Mitigation in DNN Classifiers","created":"2023-09-28","cited_by_count":0,"area":"safety"},{"id":"2401.06523","title":"Boosting Causal Additive Models","created":"2024-01-12","cited_by_count":0,"area":null},{"id":"2402.02513","title":"Early stopping by correlating online indicators in neural networks","created":"2024-02-04","cited_by_count":0,"area":null},{"id":"2402.02522","title":"Absolute convergence and error thresholds in non-active adaptive sampling","created":"2024-02-04","cited_by_count":0,"area":null},{"id":"2502.09193","title":"Countering Overfitting with Counterfactual Examples","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2505.23225","title":"Generalizability vs. Counterfactual Explainability Trade-Off","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2508.17412","title":"A Ridge Too Far: Correcting Over-Shrinkage via Negative Regularization","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2508.19028","title":"GRADSTOP: Early Stopping of Gradient Descent via Posterior Sampling","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2512.20562","title":"Shallow Neural Networks Learn Low-Degree Spherical Polynomials with Feature Learning by Learnable Channel Attention","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2603.17160","title":"Self-Regularized Learning Methods","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2603.21062","title":"Gradient Descent with Projection Finds Over-Parameterized Neural Networks for Learning Low-Degree Polynomials with Nearly Minimax Optimal Rate","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2604.26888","title":"Multiple Additive Neural Networks for Structured and Unstructured Data","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.14524","title":"Large Dimensional Kernel Ridge Regression: Extending to Product Kernels","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.02740","title":"ScoreStop: Gradient-based early stopping using functional score tests","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.22474","title":"Beyond Negative-Ridge Endpoints: Mixed-Sign Spectral Regularization via Negative-Shifted Gradient Descent","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.04927","title":"Optimal Training-Time Scaling in Gradual Adaptation","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.24210","title":"A Data-dependent Early Stopping Rule using Rademacher Complexity with L1-norm","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.25513","title":"Adaptive Regularization for Random Features: A Neighboring Early-Stopping Rule with Oracle-Rate Guarantees","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.25706","title":"Fast rates in Bayesian online learning with approximate posteriors","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.11712","title":"Generalization Analysis of Distributed Kernel-based Robust Gradient Descent Algorithms","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.21017","title":"A Smoothed Discrepancy Principle for Random Feature Methods and Neural Networks","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.26951","title":"Rolling Conformal Prediction in Sequential Model Training","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.02780","title":"Controlling Polar Exposure to Delay Memorization in Diffusion Models","created":"2026-10-02","cited_by_count":0,"area":"diffusion"},{"id":"2610.04907","title":"Why Subliminal Learning Needs So Much Data: A Noisy Inverse View through Steering Vector Recovery","created":"2026-10-04","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}