{"total":95,"rows":[{"id":"2006.13198","title":"Spectral Bias and Task-Model Alignment Explain Generalization in Kernel Regression and Infinitely Wide Neural Networks","created":"2020-06-23","cited_by_count":166,"area":"alignment"},{"id":"2105.14368","title":"Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation","created":"2021-05-29","cited_by_count":132,"area":null},{"id":"2101.10588","title":"Generalization error of random features and kernel methods: hypercontractivity and kernel matrix concentration","created":"2021-01-26","cited_by_count":110,"area":null},{"id":"2202.08087","title":"Extended Unconstrained Features Model for Exploring Deep Neural Collapse","created":"2022-02-16","cited_by_count":102,"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":"2109.02355","title":"A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning","created":"2021-09-06","cited_by_count":57,"area":null},{"id":"2405.11751","title":"Asymptotic theory of in-context learning by linear attention","created":"2024-05-20","cited_by_count":55,"area":null},{"id":"2301.00437","title":"Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data","created":"2023-01-01","cited_by_count":40,"area":null},{"id":"2102.01117","title":"SGD Generalizes Better Than GD (And Regularization Doesn't Help)","created":"2021-02-01","cited_by_count":38,"area":null},{"id":"2201.11489","title":"The Implicit Bias of Benign Overfitting","created":"2022-01-27","cited_by_count":38,"area":null},{"id":"2309.09725","title":"Neural Collapse for Unconstrained Feature Model under Cross-entropy Loss with Imbalanced Data","created":"2023-09-18","cited_by_count":38,"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":"2210.16658","title":"Perturbation Analysis of Neural Collapse","created":"2022-10-29","cited_by_count":35,"area":null},{"id":"2310.02541","title":"Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data","created":"2023-10-04","cited_by_count":33,"area":null},{"id":"2104.04244","title":"How rotational invariance of common kernels prevents generalization in high dimensions","created":"2021-04-09","cited_by_count":32,"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":"2104.09732","title":"Knowledge Distillation as Semiparametric Inference","created":"2021-04-20","cited_by_count":29,"area":"distill"},{"id":"2209.15259","title":"On the Impossible Safety of Large AI Models","created":"2022-09-30","cited_by_count":28,"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":"2403.08160","title":"Asymptotics of Random Feature Regression Beyond the Linear Scaling Regime","created":"2024-03-13","cited_by_count":26,"area":null},{"id":"2306.08321","title":"Nonparametric regression using over-parameterized shallow ReLU neural networks","created":"2023-06-14","cited_by_count":24,"area":null},{"id":"2308.13431","title":"Six Lectures on Linearized Neural Networks","created":"2023-08-25","cited_by_count":20,"area":null},{"id":"2307.01951","title":"A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks","created":"2023-07-04","cited_by_count":19,"area":null},{"id":"2412.07684","title":"The Pitfalls of Memorization: When Memorization Hurts Generalization","created":"2024-12-10","cited_by_count":19,"area":null},{"id":"2202.12328","title":"Cutting Some Slack for SGD with Adaptive Polyak Stepsizes","created":"2022-02-24","cited_by_count":18,"area":null},{"id":"2110.11805","title":"Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model","created":"2021-10-22","cited_by_count":17,"area":null},{"id":"2410.01774","title":"Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context","created":"2024-10-02","cited_by_count":15,"area":null},{"id":"2101.02696","title":"Accelerated, Optimal, and Parallel: Some Results on Model-Based Stochastic Optimization","created":"2021-01-07","cited_by_count":14,"area":null},{"id":"2202.09889","title":"Memorize to Generalize: on the Necessity of Interpolation in High Dimensional Linear Regression","created":"2022-02-20","cited_by_count":14,"area":null},{"id":"2402.18551","title":"Implicit Optimization Bias of Next-Token Prediction in Linear Models","created":"2024-02-28","cited_by_count":14,"area":null},{"id":"2102.09645","title":"SVRG Meets AdaGrad: Painless Variance Reduction","created":"2021-02-18","cited_by_count":13,"area":null},{"id":"2103.04554","title":"Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models","created":"2021-03-08","cited_by_count":13,"area":null},{"id":"2205.13525","title":"On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions","created":"2022-05-26","cited_by_count":13,"area":null},{"id":"2202.02877","title":"HARFE: Hard-Ridge Random Feature Expansion","created":"2022-02-06","cited_by_count":12,"area":null},{"id":"2204.14126","title":"Wide and Deep Neural Networks Achieve Optimality for Classification","created":"2022-04-29","cited_by_count":12,"area":null},{"id":"2406.06838","title":"Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes","created":"2024-06-10","cited_by_count":12,"area":null},{"id":"2304.02912","title":"Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach","created":"2023-04-06","cited_by_count":11,"area":null},{"id":"2506.10801","title":"Dense Associative Memory with Epanechnikov Energy","created":"2025-06-12","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":"2208.03848","title":"Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality","created":"2022-08-08","cited_by_count":9,"area":null},{"id":"2410.09638","title":"On Goodhart's law, with an application to value alignment","created":"2024-10-12","cited_by_count":9,"area":null},{"id":"2209.09315","title":"Deep Linear Networks can Benignly Overfit when Shallow Ones Do","created":"2022-09-19","cited_by_count":8,"area":null},{"id":"2110.11477","title":"Conditioning of Random Feature Matrices: Double Descent and Generalization Error","created":"2021-10-21","cited_by_count":7,"area":null},{"id":"2207.11621","title":"A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors","created":"2022-07-23","cited_by_count":7,"area":null},{"id":"2305.13588","title":"Deep Learning with Kernels through RKHM and the Perron-Frobenius Operator","created":"2023-05-23","cited_by_count":7,"area":null},{"id":"2111.07041","title":"Minimax Supervised Clustering in the Anisotropic Gaussian Mixture Model: A new take on Robust Interpolation","created":"2021-11-13","cited_by_count":6,"area":null},{"id":"2302.02904","title":"Rethinking Gauss-Newton for learning over-parameterized models","created":"2023-02-06","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":"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":"2302.07263","title":"Interpolation Learning With Minimum Description Length","created":"2023-02-14","cited_by_count":5,"area":null},{"id":"2305.11957","title":"Towards understanding neural collapse in supervised contrastive learning with the information bottleneck method","created":"2023-05-19","cited_by_count":5,"area":null},{"id":"2112.03411","title":"Extrapolation Frameworks in Cognitive Psychology Suitable for Study of Image Classification Models","created":"2021-12-06","cited_by_count":4,"area":null},{"id":"2206.01332","title":"Optimal Activation Functions for the Random Features Regression Model","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2206.07199","title":"Benefits of Additive Noise in Composing Classes with Bounded Capacity","created":"2022-06-14","cited_by_count":4,"area":null},{"id":"2302.02607","title":"Target-based Surrogates for Stochastic Optimization","created":"2023-02-06","cited_by_count":4,"area":"offlinerl"},{"id":"2305.06894","title":"Reinterpreting causal discovery as the task of predicting unobserved joint statistics","created":"2023-05-11","cited_by_count":4,"area":null},{"id":"2306.00342","title":"Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networks","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2311.14609","title":"Analysis of the expected $L_2$ error of an over-parametrized deep neural network estimate learned by gradient descent without regularization","created":"2023-11-24","cited_by_count":4,"area":null},{"id":"2102.12066","title":"On the Minimal Error of Empirical Risk Minimization","created":"2021-02-24","cited_by_count":3,"area":null},{"id":"2206.13347","title":"Benign overfitting and adaptive nonparametric regression","created":"2022-06-27","cited_by_count":3,"area":null},{"id":"2210.17070","title":"Private optimization in the interpolation regime: faster rates and hardness results","created":"2022-10-31","cited_by_count":3,"area":null},{"id":"2305.18508","title":"On the Variance, Admissibility, and Stability of Empirical Risk Minimization","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2408.16101","title":"Generative Bayesian Computation for Maximum Expected Utility","created":"2024-08-28","cited_by_count":3,"area":null},{"id":"2410.13749","title":"Supervised Kernel Thinning","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2503.00229","title":"Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2510.01404","title":"How Well do Diffusion Policies Learn Kinematic Constraint Manifolds?","created":"2025-10-01","cited_by_count":3,"area":"diffusion"},{"id":"2105.10373","title":"A Precise Performance Analysis of Support Vector Regression","created":"2021-05-21","cited_by_count":2,"area":null},{"id":"2202.09054","title":"Interpolation and Regularization for Causal Learning","created":"2022-02-18","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":"2501.05458","title":"Generative Modeling: A Review","created":"2024-12-24","cited_by_count":2,"area":null},{"id":"2502.06765","title":"Are all models wrong? Fundamental limits in distribution-free empirical model falsification","created":"2025-02-10","cited_by_count":2,"area":null},{"id":"2502.07480","title":"Beyond Benign Overfitting in Nadaraya-Watson Interpolators","created":"2025-02-11","cited_by_count":2,"area":null},{"id":"2503.17020","title":"Benign Overfitting with Quantum Kernels","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2509.25783","title":"Sharpness of Minima in Deep Matrix Factorization","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2202.05245","title":"Benign-Overfitting in Conditional Average Treatment Effect Prediction with Linear Regression","created":"2022-02-10","cited_by_count":1,"area":null},{"id":"2202.11817","title":"Benefit of Interpolation in Nearest Neighbor Algorithms","created":"2022-02-23","cited_by_count":1,"area":null},{"id":"2205.09342","title":"Consistent Interpolating Ensembles via the Manifold-Hilbert Kernel","created":"2022-05-19","cited_by_count":1,"area":null},{"id":"2401.06738","title":"(Accelerated) Noise-adaptive Stochastic Heavy-Ball Momentum","created":"2024-01-12","cited_by_count":1,"area":null},{"id":"2411.05228","title":"Solving Hidden Monotone Variational Inequalities with Surrogate Losses","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2507.11187","title":"Striking the Perfect Balance: Preserving Privacy While Boosting Utility in Collaborative Medical Prediction Platforms","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2601.16070","title":"On damage of interpolation to adversarial robustness in regression","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2602.09405","title":"Is Memorization Helpful or Harmful? Prior Information Sets the Threshold","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2603.13872","title":"On Interpolation Formulas Describing Neural Network Generalization","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2206.03254","title":"Demystifying the Global Convergence Puzzle of Learning Over-parameterized ReLU Nets in Very High Dimensions","created":"2022-06-05","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":"2305.18423","title":"On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences","created":"2023-05-28","cited_by_count":0,"area":null},{"id":"2311.03201","title":"Spatial Process Approximations: Assessing Their Necessity","created":"2023-11-06","cited_by_count":0,"area":null},{"id":"2404.02378","title":"Faster Convergence of Stochastic Accelerated Gradient Descent under Interpolation","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2405.07619","title":"Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent","created":"2024-05-13","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":"2408.03769","title":"Nadaraya-Watson kernel smoothing as a random energy model","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2509.20789","title":"Aligning Inductive Bias for Data-Efficient Generalization in State Space Models","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2604.08872","title":"How does Chain of Thought decompose complex tasks?","created":"2026-04-10","cited_by_count":0,"area":"lr"},{"id":"2605.29819","title":"The Interplay Between Interpolation and Aggregation in Regression: Optimal Sample Complexity","created":"2026-05-28","cited_by_count":0,"area":null}],"next_cursor":null}