{"total":69,"rows":[{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363,"area":null},{"id":"2209.05364","title":"If Influence Functions are the Answer, Then What is the Question?","created":"2022-09-12","cited_by_count":144,"area":null},{"id":"2402.07712","title":"Model Collapse Demystified: The Case of Regression","created":"2024-02-12","cited_by_count":82,"area":"synth"},{"id":"2103.01550","title":"Label-Imbalanced and Group-Sensitive Classification under Overparameterization","created":"2021-03-02","cited_by_count":74,"area":null},{"id":"2405.00592","title":"Scaling and renormalization in high-dimensional regression","created":"2024-05-01","cited_by_count":50,"area":null},{"id":"2207.06569","title":"Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting","created":"2022-07-14","cited_by_count":36,"area":null},{"id":"2306.03534","title":"Continual Learning in Linear Classification on Separable Data","created":"2023-06-06","cited_by_count":34,"area":null},{"id":"2406.06213","title":"A Statistical Theory of Regularization-Based Continual Learning","created":"2024-06-10","cited_by_count":33,"area":null},{"id":"2108.04552","title":"The Benefits of Implicit Regularization from SGD in Least Squares Problems","created":"2021-08-10","cited_by_count":32,"area":null},{"id":"2212.14032","title":"On Implicit Bias in Overparameterized Bilevel Optimization","created":"2022-12-28","cited_by_count":30,"area":null},{"id":"2312.15995","title":"Generalization in Kernel Regression Under Realistic Assumptions","created":"2023-12-26","cited_by_count":27,"area":null},{"id":"2110.03922","title":"The Eigenlearning Framework: A Conservation Law Perspective on Kernel Regression and Wide Neural Networks","created":"2021-10-08","cited_by_count":26,"area":null},{"id":"2112.03215","title":"Multi-scale Feature Learning Dynamics: Insights for Double Descent","created":"2021-12-06","cited_by_count":24,"area":null},{"id":"2210.11075","title":"Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise","created":"2022-10-20","cited_by_count":22,"area":null},{"id":"2105.00303","title":"RATT: Leveraging Unlabeled Data to Guarantee Generalization","created":"2021-05-01","cited_by_count":20,"area":null},{"id":"2108.02883","title":"Interpolation can hurt robust generalization even when there is no noise","created":"2021-08-05","cited_by_count":15,"area":null},{"id":"2202.09028","title":"On the Implicit Bias Towards Minimal Depth of Deep Neural Networks","created":"2022-02-18","cited_by_count":12,"area":null},{"id":"2205.07331","title":"Sobolev Acceleration and Statistical Optimality for Learning Elliptic Equations via Gradient Descent","created":"2022-05-15","cited_by_count":11,"area":null},{"id":"2403.06392","title":"Towards Robust Out-of-Distribution Generalization Bounds via Sharpness","created":"2024-03-11","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":"2305.18496","title":"Generalized equivalences between subsampling and ridge regularization","created":"2023-05-29","cited_by_count":10,"area":null},{"id":"2206.01378","title":"Regularization-wise double descent: Why it occurs and how to eliminate it","created":"2022-06-03","cited_by_count":9,"area":null},{"id":"2502.13283","title":"Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression","created":"2025-02-18","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":"2506.06501","title":"Optimal Rates in Continual Linear Regression via Increasing Regularization","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2211.06077","title":"Overparameterized random feature regression with nearly orthogonal data","created":"2022-11-11","cited_by_count":7,"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":"2202.09885","title":"On Optimal Early Stopping: Over-informative versus Under-informative Parametrization","created":"2022-02-20","cited_by_count":4,"area":null},{"id":"2301.13486","title":"Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond","created":"2023-01-31","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":"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":"2403.08585","title":"Improving Implicit Regularization of SGD with Preconditioning for Least Square Problems","created":"2024-03-13","cited_by_count":3,"area":null},{"id":"2507.03404","title":"On the Effectiveness of the z-Transform Method in Quadratic Optimization","created":"2025-07-04","cited_by_count":3,"area":null},{"id":"2604.18450","title":"Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2105.13440","title":"Non-negative matrix factorization algorithms generally improve topic model fits","created":"2021-05-27","cited_by_count":2,"area":null},{"id":"2204.04476","title":"High-dimensional Asymptotics of Langevin Dynamics in Spiked Matrix Models","created":"2022-04-09","cited_by_count":2,"area":null},{"id":"2306.16838","title":"Fast Robust Kernel Regression through Sign Gradient Descent with Early Stopping","created":"2023-06-29","cited_by_count":2,"area":null},{"id":"2503.05542","title":"Comparing regularisation paths of (conjugate) gradient estimators in ridge regression","created":"2025-03-07","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":"2203.11992","title":"Resonance in Weight Space: Covariate Shift Can Drive Divergence of SGD with Momentum","created":"2022-03-22","cited_by_count":1,"area":null},{"id":"2311.11093","title":"Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2405.08825","title":"Thermodynamic limit in learning period three","created":"2024-05-12","cited_by_count":1,"area":null},{"id":"2408.04313","title":"Better Locally Private Sparse Estimation Given Multiple Samples Per User","created":"2024-08-08","cited_by_count":1,"area":null},{"id":"2408.15784","title":"Implicit Regularization Paths of Weighted Neural Representations","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2603.20967","title":"Hard labels sampled from sparse targets mislead rotation invariant algorithms","created":"2026-03-21","cited_by_count":1,"area":null},{"id":"2605.05436","title":"Estimating Implicit Regularization in Deep Learning","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2609.26392","title":"Double Descent and Malign Overfitting in Diffusion Models","created":"2026-09-22","cited_by_count":1,"area":"diffusion"},{"id":"2110.03273","title":"AgFlow: Fast Model Selection of Penalized PCA via Implicit Regularization Effects of Gradient Flow","created":"2021-10-07","cited_by_count":0,"area":null},{"id":"2201.05405","title":"The Implicit Regularization of Momentum Gradient Descent with Early Stopping","created":"2022-01-14","cited_by_count":0,"area":null},{"id":"2201.08311","title":"Accelerated Gradient Flow: Risk, Stability, and Implicit Regularization","created":"2022-01-20","cited_by_count":0,"area":null},{"id":"2301.11414","title":"A Simple Algorithm For Scaling Up Kernel Methods","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2304.00320","title":"Doubly Stochastic Models: Learning with Unbiased Label Noises and Inference Stability","created":"2023-04-01","cited_by_count":0,"area":null},{"id":"2406.03696","title":"Error dynamics of mini-batch gradient descent with random reshuffling for least squares regression","created":"2024-06-06","cited_by_count":0,"area":null},{"id":"2406.09183","title":"Ridge interpolators in correlated factor regression models -- exact risk analysis","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2406.09199","title":"Precise analysis of ridge interpolators under heavy correlations -- a Random Duality Theory view","created":"2024-06-13","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":"2510.19020","title":"Calibrated Principal Component Regression","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2605.30059","title":"Ridge Regression from Poisson Resetting: A Renewal Perspective on Spectral Regularization","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.00243","title":"Dynamics and Representation Structure of Local Approximations to Gradient-Based Learning in Linear Recurrent Neural Networks","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.10410","title":"TSCoNet: A Two-Stage Copula CNN-LSTM for Uncertainty-Aware Spatio-Temporal Forecasting","created":"2026-07-11","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":"2609.16262","title":"Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Descent","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.19076","title":"Double descent is the principle of least action","created":"2026-09-16","cited_by_count":0,"area":null},{"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"},{"id":"2610.16845","title":"Feature Normalization under Finite Training Budgets","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}