{"total":148,"rows":[{"id":"2205.01445","title":"High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation","created":"2022-05-03","cited_by_count":150,"area":null},{"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":"2203.06176","title":"More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize","created":"2022-03-11","cited_by_count":91,"area":null},{"id":"2503.02113","title":"Deep Learning is Not So Mysterious or Different","created":"2025-03-03","cited_by_count":56,"area":null},{"id":"2106.03791","title":"Learning Gaussian Mixtures with Generalised Linear Models: Precise Asymptotics in High-dimensions","created":"2021-06-07","cited_by_count":54,"area":null},{"id":"2405.00592","title":"Scaling and renormalization in high-dimensional regression","created":"2024-05-01","cited_by_count":50,"area":null},{"id":"2310.07891","title":"A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks","created":"2023-10-11","cited_by_count":49,"area":null},{"id":"2303.01372","title":"High-dimensional analysis of double descent for linear regression with random projections","created":"2023-03-02","cited_by_count":47,"area":null},{"id":"2302.00401","title":"Deterministic equivalent and error universality of deep random features learning","created":"2023-02-01","cited_by_count":35,"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":"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":"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":"2205.13303","title":"Gaussian Universality of Perceptrons with Random Labels","created":"2022-05-26","cited_by_count":26,"area":null},{"id":"2302.08923","title":"Are Gaussian data all you need? Extents and limits of universality in high-dimensional generalized linear estimation","created":"2023-02-17","cited_by_count":26,"area":null},{"id":"2310.16441","title":"Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding","created":"2023-10-25","cited_by_count":25,"area":null},{"id":"2203.03597","title":"Fast Rates for Noisy Interpolation Require Rethinking the Effects of Inductive Bias","created":"2022-03-07","cited_by_count":22,"area":null},{"id":"2308.13431","title":"Six Lectures on Linearized Neural Networks","created":"2023-08-25","cited_by_count":20,"area":null},{"id":"2205.06798","title":"Sharp Asymptotics of Kernel Ridge Regression Beyond the Linear Regime","created":"2022-05-13","cited_by_count":19,"area":null},{"id":"2412.06126","title":"UCB algorithms for multi-armed bandits: Precise regret and adaptive inference","created":"2024-12-09","cited_by_count":19,"area":null},{"id":"2311.14646","title":"More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory","created":"2023-11-24","cited_by_count":18,"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":"2501.19195","title":"Rethinking Early Stopping: Refine, Then Calibrate","created":"2025-01-31","cited_by_count":17,"area":null},{"id":"2111.05987","title":"Tight bounds for minimum l1-norm interpolation of noisy data","created":"2021-11-10","cited_by_count":16,"area":null},{"id":"2210.12760","title":"On double-descent in uncertainty quantification in overparametrized models","created":"2022-10-23","cited_by_count":16,"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":"2207.10199","title":"Provably tuning the ElasticNet across instances","created":"2022-07-20","cited_by_count":14,"area":null},{"id":"2502.20003","title":"Asymptotics of Non-Convex Generalized Linear Models in High-Dimensions: A proof of the replica formula","created":"2025-02-27","cited_by_count":14,"area":null},{"id":"2103.05524","title":"On the interplay between data structure and loss function in classification problems","created":"2021-03-09","cited_by_count":13,"area":null},{"id":"2402.13999","title":"Asymptotics of Learning with Deep Structured (Random) Features","created":"2024-02-21","cited_by_count":13,"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":"2312.08893","title":"Solving Dense Linear Systems Faster Than via Preconditioning","created":"2023-12-14","cited_by_count":12,"area":null},{"id":"2409.13904","title":"High-dimensional learning of narrow neural networks","created":"2024-09-20","cited_by_count":12,"area":null},{"id":"2203.11864","title":"On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes","created":"2022-03-22","cited_by_count":11,"area":null},{"id":"2210.07612","title":"Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes","created":"2022-10-14","cited_by_count":11,"area":null},{"id":"2304.13016","title":"Subsample Ridge Ensembles: Equivalences and Generalized Cross-Validation","created":"2023-04-25","cited_by_count":11,"area":null},{"id":"2310.04357","title":"Asymptotically free sketched ridge ensembles: Risks, cross-validation, and tuning","created":"2023-10-06","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":"2506.06280","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","created":"2025-06-06","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":"2509.22341","title":"Preventing Model Collapse Under Overparametrization: Optimal Mixing Ratios for Interpolation Learning and Ridge Regression","created":"2025-09-26","cited_by_count":9,"area":"synth"},{"id":"2201.08082","title":"Kernel Methods and Multi-layer Perceptrons Learn Linear Models in High Dimensions","created":"2022-01-20","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":"2403.07264","title":"Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2406.10327","title":"Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting","created":"2024-06-14","cited_by_count":8,"area":null},{"id":"2408.04607","title":"Risk and cross validation in ridge regression with correlated samples","created":"2024-08-08","cited_by_count":8,"area":null},{"id":"2505.18346","title":"On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective","created":"2025-05-23","cited_by_count":8,"area":null},{"id":"2509.26551","title":"Pretrain-Test Task Alignment Governs Generalization in In-Context Learning","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2107.05143","title":"Derivatives and residual distribution of regularized M-estimators with application to adaptive tuning","created":"2021-07-11","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":"2302.01088","title":"Sketched Ridgeless Linear Regression: The Role of Downsampling","created":"2023-02-02","cited_by_count":7,"area":null},{"id":"2311.14823","title":"Revisiting Quantum Algorithms for Linear Regressions: Quadratic Speedups without Data-Dependent Parameters","created":"2023-11-24","cited_by_count":7,"area":null},{"id":"2512.22768","title":"Understanding the Mechanisms of Fast Hyperparameter Transfer","created":"2025-12-28","cited_by_count":7,"area":null},{"id":"2103.05621","title":"The Common Intuition to Transfer Learning Can Win or Lose: Case Studies for Linear Regression","created":"2021-03-09","cited_by_count":6,"area":null},{"id":"2103.14723","title":"Lower Bounds on the Generalization Error of Nonlinear Learning Models","created":"2021-03-26","cited_by_count":6,"area":null},{"id":"2110.10956","title":"Data splitting improves statistical performance in overparametrized regimes","created":"2021-10-21","cited_by_count":6,"area":null},{"id":"2402.02697","title":"Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures","created":"2024-02-05","cited_by_count":6,"area":null},{"id":"2505.07640","title":"Certified Data Removal Under High-dimensional Settings","created":"2025-05-12","cited_by_count":6,"area":"safety"},{"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":"2201.04545","title":"On generalization bounds for deep networks based on loss surface implicit regularization","created":"2022-01-12","cited_by_count":5,"area":null},{"id":"2212.06757","title":"Gradient flow in the gaussian covariate model: exact solution of learning curves and multiple descent structures","created":"2022-12-13","cited_by_count":5,"area":null},{"id":"2310.01374","title":"Corrected generalized cross-validation for finite ensembles of penalized estimators","created":"2023-10-02","cited_by_count":5,"area":null},{"id":"2403.20200","title":"High-dimensional analysis of ridge regression for non-identically distributed data with a variance profile","created":"2024-03-29","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":"2204.08369","title":"Benign Overfitting in Time Series Linear Models with Over-Parameterization","created":"2022-04-18","cited_by_count":4,"area":null},{"id":"2206.10291","title":"Algorithmic Gaussianization through Sketching: Converting Data into Sub-gaussian Random Designs","created":"2022-06-21","cited_by_count":4,"area":null},{"id":"2305.14689","title":"Least Squares Regression Can Exhibit Under-Parameterized Double Descent","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2402.13622","title":"Analysis of Bootstrap and Subsampling in High-dimensional Regularized Regression","created":"2024-02-21","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":"2404.09779","title":"A replica analysis of under-bagging","created":"2024-04-15","cited_by_count":4,"area":null},{"id":"2405.05865","title":"Faster Linear Systems and Matrix Norm Approximation via Multi-level Sketched Preconditioning","created":"2024-05-09","cited_by_count":4,"area":null},{"id":"2406.03171","title":"High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization","created":"2024-06-05","cited_by_count":4,"area":null},{"id":"2406.11666","title":"ROTI-GCV: Generalized Cross-Validation for right-ROTationally Invariant Data","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2410.05609","title":"The Breakdown of Gaussian Universality in Classification of High-dimensional Linear Factor Mixtures","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2506.13139","title":"Random Matrix Theory for Deep Learning: Beyond Eigenvalues of Linear Models","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2510.01303","title":"Low Rank Gradients and Where to Find Them","created":"2025-10-01","cited_by_count":4,"area":null},{"id":"2103.04557","title":"Asymptotics of Ridge Regression in Convolutional Models","created":"2021-03-08","cited_by_count":3,"area":null},{"id":"2110.11258","title":"On Optimal Interpolation In Linear Regression","created":"2021-10-21","cited_by_count":3,"area":null},{"id":"2206.07256","title":"Noise Covariance Estimation in Multi-Task High-dimensional Linear Models","created":"2022-06-15","cited_by_count":3,"area":null},{"id":"2209.12651","title":"Learning Variational Models with Unrolling and Bilevel Optimization","created":"2022-09-26","cited_by_count":3,"area":null},{"id":"2309.03354","title":"Ensemble linear interpolators: The role of ensembling","created":"2023-09-06","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":"2509.21650","title":"Understanding and Enhancing Mask-Based Pretraining towards Universal Representations","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2202.09054","title":"Interpolation and Regularization for Causal Learning","created":"2022-02-18","cited_by_count":2,"area":null},{"id":"2306.15915","title":"Transfer Learning with Random Coefficient Ridge Regression","created":"2023-06-28","cited_by_count":2,"area":null},{"id":"2310.00729","title":"Spectral Neural Networks: Approximation Theory and Optimization Landscape","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2404.12481","title":"Understanding Optimal Feature Transfer via a Fine-Grained Bias-Variance Analysis","created":"2024-04-18","cited_by_count":2,"area":null},{"id":"2410.13991","title":"Generalization for Least Squares Regression With Simple Spiked Covariances","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2410.16150","title":"Modeling Structured Data Learning with Restricted Boltzmann Machines in the Teacher-Student Setting","created":"2024-10-21","cited_by_count":2,"area":"distill"},{"id":"2411.17807","title":"A solvable generative model with a linear, one-step denoiser","created":"2024-11-26","cited_by_count":2,"area":"diffusion"},{"id":"2501.16226","title":"The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model","created":"2025-01-27","cited_by_count":2,"area":"distill"},{"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":"2504.03035","title":"High-dimensional ridge regression with random features for non-identically distributed data with a variance profile","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2505.15175","title":"A Linear Approach to Data Poisoning","created":"2025-05-21","cited_by_count":2,"area":"safety"},{"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":"2103.00500","title":"Asymptotic Risk of Overparameterized Likelihood Models: Double Descent Theory for Deep Neural Networks","created":"2021-02-28","cited_by_count":1,"area":null},{"id":"2110.08500","title":"On Model Selection Consistency of Lasso for High-Dimensional Ising Models","created":"2021-10-16","cited_by_count":1,"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}],"next_cursor":"100"}