{"total":25,"rows":[{"id":"2406.08466","title":"Scaling Laws in Linear Regression: Compute, Parameters, and Data","created":"2024-06-12","cited_by_count":57,"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":"2405.17583","title":"Understanding Forgetting in Continual Learning with Linear Regression","created":"2024-05-27","cited_by_count":30,"area":null},{"id":"2303.10263","title":"Fixed Design Analysis of Regularization-Based Continual Learning","created":"2023-03-17","cited_by_count":24,"area":null},{"id":"2302.10160","title":"Pseudo-Labeling for Kernel Ridge Regression under Covariate Shift","created":"2023-02-20","cited_by_count":17,"area":null},{"id":"2301.13371","title":"Demystifying Disagreement-on-the-Line in High Dimensions","created":"2023-01-31","cited_by_count":12,"area":null},{"id":"2506.08415","title":"Improved Scaling Laws in Linear Regression via Data Reuse","created":"2025-06-10","cited_by_count":11,"area":null},{"id":"2602.03702","title":"Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging","created":"2026-02-03","cited_by_count":10,"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":"2303.02255","title":"Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron","created":"2023-03-03","cited_by_count":8,"area":null},{"id":"2403.17592","title":"On the Benefits of Over-parameterization for Out-of-Distribution Generalization","created":"2024-03-26","cited_by_count":7,"area":null},{"id":"2510.14717","title":"Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling","created":"2025-10-16","cited_by_count":6,"area":null},{"id":"2504.04039","title":"Memory-Statistics Tradeoff in Continual Learning with Structural Regularization","created":"2025-04-05","cited_by_count":5,"area":null},{"id":"2503.01314","title":"Scaling Law Phenomena Across Regression Paradigms: Multiple and Kernel Approaches","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2510.15337","title":"Transfer Learning for Benign Overfitting in High-Dimensional Linear Regression","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2312.17463","title":"Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift","created":"2023-12-29","cited_by_count":2,"area":null},{"id":"2606.19179","title":"Compute Efficiency and Serial Runtime Tradeoffs for Stochastic Momentum Methods","created":"2026-06-17","cited_by_count":2,"area":null},{"id":"2512.05084","title":"Gradient Descent with Provably Tuned Learning-rate Schedules","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2403.16451","title":"DeepMachining: Online Prediction of Machining Errors of Lathe Machines","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2408.00359","title":"Memorization Capacity for Additive Fine-Tuning with Small ReLU Networks","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2409.03543","title":"Prediction Accuracy & Reliability: Classification and Object Localization under Distribution Shift","created":"2024-09-05","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":"2609.34667","title":"Two-Timescale Fine-tuning Provably Learns New Features for Two-Layer ReLU Networks","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34756","title":"Statistical Benefits of Fine-Tuning from Pretrained Initialization in Diagonal Linear Networks","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.16845","title":"Feature Normalization under Finite Training Budgets","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}