{"total":24,"rows":[{"id":"2302.11055","title":"SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics","created":"2023-02-21","cited_by_count":143,"area":null},{"id":"2310.08391","title":"How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?","created":"2023-10-12","cited_by_count":96,"area":null},{"id":"2103.12692","title":"Benign Overfitting of Constant-Stepsize SGD for Linear Regression","created":"2021-03-23","cited_by_count":71,"area":null},{"id":"2406.08466","title":"Scaling Laws in Linear Regression: Compute, Parameters, and Data","created":"2024-06-12","cited_by_count":57,"area":null},{"id":"2110.06198","title":"Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression","created":"2021-10-12","cited_by_count":38,"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":"2405.17583","title":"Understanding Forgetting in Continual Learning with Linear Regression","created":"2024-05-27","cited_by_count":30,"area":null},{"id":"2208.01857","title":"The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift","created":"2022-08-03","cited_by_count":26,"area":null},{"id":"2310.06771","title":"Correlated Noise Provably Beats Independent Noise for Differentially Private Learning","created":"2023-10-10","cited_by_count":23,"area":null},{"id":"2306.11497","title":"Convergence and concentration properties of constant step-size SGD through Markov chains","created":"2023-06-20","cited_by_count":11,"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":"2206.09136","title":"Provable Generalization of Overparameterized Meta-learning Trained with SGD","created":"2022-06-18","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":"2409.09745","title":"The Optimality of (Accelerated) SGD for High-Dimensional Quadratic Optimization","created":"2024-09-15","cited_by_count":8,"area":null},{"id":"2311.14222","title":"Risk Bounds of Accelerated SGD for Overparameterized Linear Regression","created":"2023-11-23","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":"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":"2110.06910","title":"On the Double Descent of Random Features Models Trained with SGD","created":"2021-10-13","cited_by_count":5,"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":"2411.13169","title":"A Unified Analysis for Finite Weight Averaging","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2508.14338","title":"On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks","created":"2025-08-20","cited_by_count":2,"area":null},{"id":"2212.04014","title":"Statistical and Computational Guarantees for Influence Diagnostics","created":"2022-12-08","cited_by_count":1,"area":null},{"id":"2210.11562","title":"Local SGD in Overparameterized Linear Regression","created":"2022-10-20","cited_by_count":0,"area":null}],"next_cursor":null}