{"total":69,"rows":[{"id":"2102.08127","title":"Learning curves of generic features maps for realistic datasets with a teacher-student model","created":"2021-02-16","cited_by_count":126,"area":"distill"},{"id":"2105.15004","title":"Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime","created":"2021-05-31","cited_by_count":96,"area":null},{"id":"2402.07712","title":"Model Collapse Demystified: The Case of Regression","created":"2024-02-12","cited_by_count":82,"area":"synth"},{"id":"2406.08466","title":"Scaling Laws in Linear Regression: Compute, Parameters, and Data","created":"2024-06-12","cited_by_count":57,"area":null},{"id":"2409.17858","title":"How Feature Learning Can Improve Neural Scaling Laws","created":"2024-09-26","cited_by_count":56,"area":null},{"id":"2405.00592","title":"Scaling and renormalization in high-dimensional regression","created":"2024-05-01","cited_by_count":50,"area":null},{"id":"2102.03183","title":"Last iterate convergence of SGD for Least-Squares in the Interpolation regime","created":"2021-02-05","cited_by_count":42,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2303.14942","title":"On the Optimality of Misspecified Spectral Algorithms","created":"2023-03-27","cited_by_count":28,"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":"2202.05318","title":"Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning","created":"2022-02-10","cited_by_count":23,"area":null},{"id":"2206.07252","title":"Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions","created":"2022-06-15","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":"2305.07241","title":"On the Optimality of Misspecified Kernel Ridge Regression","created":"2023-05-12","cited_by_count":20,"area":null},{"id":"2201.12655","title":"Error Scaling Laws for Kernel Classification under Source and Capacity Conditions","created":"2022-01-29","cited_by_count":17,"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":"2106.07148","title":"On the Sample Complexity of Learning under Invariance and Geometric Stability","created":"2021-06-14","cited_by_count":13,"area":null},{"id":"2410.04642","title":"The Optimization Landscape of SGD Across the Feature Learning Strength","created":"2024-10-06","cited_by_count":13,"area":null},{"id":"2102.00760","title":"Fast rates in structured prediction","created":"2021-02-01","cited_by_count":11,"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":"2506.08415","title":"Improved Scaling Laws in Linear Regression via Data Reuse","created":"2025-06-10","cited_by_count":11,"area":null},{"id":"2209.12198","title":"Capacity dependent analysis for functional online learning algorithms","created":"2022-09-25","cited_by_count":10,"area":null},{"id":"2506.03470","title":"Models of Heavy-Tailed Mechanistic Universality","created":"2025-06-04","cited_by_count":10,"area":null},{"id":"2510.04780","title":"Kernel ridge regression under power-law data: spectrum and generalization","created":"2025-10-06","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":"2202.13733","title":"On the Benefits of Large Learning Rates for Kernel Methods","created":"2022-02-28","cited_by_count":8,"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":"2211.10968","title":"Statistical Optimality of Divide and Conquer Kernel-based Functional Linear Regression","created":"2022-11-20","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":"2602.06797","title":"Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup-Stable-Decay","created":"2026-02-06","cited_by_count":8,"area":null},{"id":"2502.05074","title":"Two-Point Deterministic Equivalence for Stochastic Gradient Dynamics in Linear Models","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2602.04774","title":"Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model","created":"2026-02-04","cited_by_count":7,"area":null},{"id":"2303.10758","title":"Lower Generalization Bounds for GD and SGD in Smooth Stochastic Convex Optimization","created":"2023-03-19","cited_by_count":6,"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":"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":"2602.14208","title":"Fast Catch-Up, Late Switching: Optimal Batch Size Scheduling via Functional Scaling Laws","created":"2026-02-15","cited_by_count":6,"area":null},{"id":"2102.03594","title":"Online nonparametric regression with Sobolev kernels","created":"2021-02-06","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":"2302.06757","title":"Kernelized Diffusion maps","created":"2023-02-13","cited_by_count":5,"area":null},{"id":"2302.10128","title":"Sketch In, Sketch Out: Accelerating both Learning and Inference for Structured Prediction with Kernels","created":"2023-02-20","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":"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":"2205.13255","title":"Active Labeling: Streaming Stochastic Gradients","created":"2022-05-26","cited_by_count":3,"area":null},{"id":"2407.02322","title":"Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent","created":"2024-07-02","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":"2511.18661","title":"Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2211.13549","title":"Online Regularized Learning Algorithm for Functional Data","created":"2022-11-24","cited_by_count":2,"area":null},{"id":"2410.09766","title":"Stability and Sharper Risk Bounds with Convergence Rate $\\tilde{O}(1/n^2)$","created":"2024-10-13","cited_by_count":2,"area":null},{"id":"2501.10870","title":"Fixed-Gaussian Spectral Algorithms: Minimax Optimal Rates for Misspecified Learning and Transfer","created":"2025-01-18","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":"2506.16283","title":"Random feature approximation for general spectral methods","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2105.06015","title":"Why Does Multi-Epoch Training Help?","created":"2021-05-13","cited_by_count":1,"area":null},{"id":"2106.02713","title":"Learning Curves for SGD on Structured Features","created":"2021-06-04","cited_by_count":1,"area":null},{"id":"2205.00061","title":"The Directional Bias Helps Stochastic Gradient Descent to Generalize in Kernel Regression Models","created":"2022-04-29","cited_by_count":1,"area":null},{"id":"2402.01148","title":"The Optimality of Kernel Classifiers in Sobolev Space","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2403.03669","title":"Spectral Algorithms on Manifolds through Diffusion","created":"2024-03-06","cited_by_count":1,"area":null},{"id":"2403.11696","title":"Generalization error of spectral algorithms","created":"2024-03-18","cited_by_count":1,"area":null},{"id":"2209.11629","title":"From Weakly Supervised Learning to Active Learning","created":"2022-09-23","cited_by_count":0,"area":null},{"id":"2308.15434","title":"Random feature approximation for general spectral methods","created":"2023-08-29","cited_by_count":0,"area":null},{"id":"2406.09194","title":"Benign overfitting in Fixed Dimension via Physics-Informed Learning with Smooth Inductive Bias","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2410.01394","title":"Gaussian kernel expansion with basis functions uniformly bounded in $\\mathcal{L}_{\\infty}$","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2410.14539","title":"Diffusion-based Semi-supervised Spectral Algorithm for Regression on Manifolds","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2412.18756","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","created":"2024-12-25","cited_by_count":0,"area":null},{"id":"2506.02754","title":"Safely Learning Controlled Stochastic Dynamics","created":"2025-06-03","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":"2603.11989","title":"On-Average Stability of Multipass Preconditioned SGD and Effective Dimension","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2605.20314","title":"Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2608.22953","title":"Stochastic gradient descent with initial regularization","created":"2026-08-24","cited_by_count":0,"area":null}],"next_cursor":null}