{"total":109,"rows":[{"id":"2205.10343","title":"Towards Understanding Grokking: An Effective Theory of Representation Learning","created":"2022-05-20","cited_by_count":230,"area":null},{"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":"2210.16859","title":"A Solvable Model of Neural Scaling Laws","created":"2022-10-30","cited_by_count":116,"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":"2103.10948","title":"The Shape of Learning Curves: a Review","created":"2021-03-19","cited_by_count":70,"area":null},{"id":"2304.05366","title":"The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning","created":"2023-04-11","cited_by_count":63,"area":null},{"id":"2209.03942","title":"Data Feedback Loops: Model-driven Amplification of Dataset Biases","created":"2022-09-08","cited_by_count":60,"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":"2301.11526","title":"Direct Parameterization of Lipschitz-Bounded Deep Networks","created":"2023-01-27","cited_by_count":51,"area":null},{"id":"2303.14151","title":"Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle","created":"2023-03-24","cited_by_count":37,"area":null},{"id":"2106.03212","title":"Towards an Understanding of Benign Overfitting in Neural Networks","created":"2021-06-06","cited_by_count":30,"area":null},{"id":"2102.07861","title":"Low Curvature Activations Reduce Overfitting in Adversarial Training","created":"2021-02-15","cited_by_count":29,"area":null},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2209.15259","title":"On the Impossible Safety of Large AI Models","created":"2022-09-30","cited_by_count":28,"area":null},{"id":"2201.12150","title":"Learning Curves for Decision Making in Supervised Machine Learning: A Survey","created":"2022-01-28","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":"2302.10886","title":"Some Fundamental Aspects about Lipschitz Continuity of Neural Networks","created":"2023-02-21","cited_by_count":26,"area":null},{"id":"2210.05021","title":"The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2106.02261","title":"Out-of-Distribution Generalization in Kernel Regression","created":"2021-06-04","cited_by_count":21,"area":null},{"id":"2201.06142","title":"Towards Sample-efficient Overparameterized Meta-learning","created":"2022-01-16","cited_by_count":21,"area":null},{"id":"2202.09931","title":"Deconstructing Distributions: A Pointwise Framework of Learning","created":"2022-02-20","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":"2408.08944","title":"Information-Theoretic Progress Measures reveal Grokking is an Emergent Phase Transition","created":"2024-08-16","cited_by_count":17,"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":"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":"2203.07337","title":"Phenomenology of Double Descent in Finite-Width Neural Networks","created":"2022-03-14","cited_by_count":12,"area":null},{"id":"2206.13482","title":"Understanding Benign Overfitting in Gradient-Based Meta Learning","created":"2022-06-27","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":"2406.04425","title":"On Regularization via Early Stopping for Least Squares Regression","created":"2024-06-06","cited_by_count":11,"area":null},{"id":"2203.01726","title":"Ensembles of Vision Transformers as a New Paradigm for Automated Classification in Ecology","created":"2022-03-03","cited_by_count":10,"area":null},{"id":"2205.12937","title":"Mitigating multiple descents: A model-agnostic framework for risk monotonization","created":"2022-05-25","cited_by_count":10,"area":null},{"id":"2208.09897","title":"Multiple Descent in the Multiple Random Feature Model","created":"2022-08-21","cited_by_count":10,"area":null},{"id":"2305.18496","title":"Generalized equivalences between subsampling and ridge regularization","created":"2023-05-29","cited_by_count":10,"area":null},{"id":"2605.29548","title":"Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention","created":"2026-05-28","cited_by_count":10,"area":null},{"id":"2206.01378","title":"Regularization-wise double descent: Why it occurs and how to eliminate it","created":"2022-06-03","cited_by_count":9,"area":null},{"id":"2411.00247","title":"Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond","created":"2024-10-31","cited_by_count":9,"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":"2404.07815","title":"Post-Hoc Reversal: Are We Selecting Models Prematurely?","created":"2024-04-11","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":"2110.09502","title":"Minimum $\\ell_{1}$-norm interpolators: Precise asymptotics and multiple descent","created":"2021-10-18","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":"2303.01213","title":"DSD$^2$: Can We Dodge Sparse Double Descent and Compress the Neural Network Worry-Free?","created":"2023-03-02","cited_by_count":6,"area":null},{"id":"2409.16499","title":"Learning Linear Dynamics from Bilinear Observations","created":"2024-09-24","cited_by_count":6,"area":null},{"id":"2106.04003","title":"Double Descent and Other Interpolation Phenomena in GANs","created":"2021-06-07","cited_by_count":5,"area":null},{"id":"2210.11452","title":"Global Convergence of SGD On Two Layer Neural Nets","created":"2022-10-20","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":"2407.08641","title":"How more data can hurt: Instability and regularization in next-generation reservoir computing","created":"2024-07-11","cited_by_count":5,"area":null},{"id":"2501.07652","title":"Finite Sample Identification of Partially Observed Bilinear Dynamical Systems","created":"2025-01-13","cited_by_count":5,"area":null},{"id":"2506.06866","title":"SAFE: Finding Sparse and Flat Minima to Improve Pruning","created":"2025-06-07","cited_by_count":5,"area":null},{"id":"2101.09001","title":"Linear Regression with Distributed Learning: A Generalization Error Perspective","created":"2021-01-22","cited_by_count":4,"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":"2305.14689","title":"Least Squares Regression Can Exhibit Under-Parameterized Double Descent","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2305.17332","title":"Learning Capacity: A Measure of the Effective Dimensionality of a Model","created":"2023-05-27","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":"2410.11985","title":"The Fair Language Model Paradox","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2506.07298","title":"Pre-trained Large Language Models Learn Hidden Markov Models In-context","created":"2025-06-08","cited_by_count":4,"area":null},{"id":"2107.00797","title":"Mitigating deep double descent by concatenating inputs","created":"2021-07-02","cited_by_count":3,"area":null},{"id":"2208.08003","title":"Investigating the Impact of Model Width and Density on Generalization in Presence of Label Noise","created":"2022-08-17","cited_by_count":3,"area":null},{"id":"2307.11838","title":"Data-Induced Interactions of Sparse Sensors Using Statistical Physics","created":"2023-07-21","cited_by_count":3,"area":null},{"id":"2309.09258","title":"Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets","created":"2023-09-17","cited_by_count":3,"area":null},{"id":"2309.16846","title":"Optimal Nonlinearities Improve Generalization Performance of Random Features","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2311.17539","title":"Critical Influence of Overparameterization on Sharpness-aware Minimization","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2406.16988","title":"MD tree: a model-diagnostic tree grown on loss landscape","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2506.23286","title":"Not All Explanations for Deep Learning Phenomena Are Equally Valuable","created":"2025-06-29","cited_by_count":3,"area":null},{"id":"2509.15152","title":"Asymptotic Study of In-context Learning with Random Transformers through Equivalent Models","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2102.07181","title":"Distribution Free Uncertainty for the Minimum Norm Solution of Over-parameterized Linear Regression","created":"2021-02-14","cited_by_count":2,"area":null},{"id":"2103.07986","title":"Pre-interpolation loss behaviour in neural networks","created":"2021-03-14","cited_by_count":2,"area":null},{"id":"2105.10373","title":"A Precise Performance Analysis of Support Vector Regression","created":"2021-05-21","cited_by_count":2,"area":null},{"id":"2106.04795","title":"Nonasymptotic theory for two-layer neural networks: Beyond the bias-variance trade-off","created":"2021-06-09","cited_by_count":2,"area":null},{"id":"2203.03398","title":"Estimation under Model Misspecification with Fake Features","created":"2022-03-07","cited_by_count":2,"area":null},{"id":"2211.14061","title":"A Survey of Learning Curves with Bad Behavior: or How More Data Need Not Lead to Better Performance","created":"2022-11-25","cited_by_count":2,"area":null},{"id":"2302.13259","title":"Can we avoid Double Descent in Deep Neural Networks?","created":"2023-02-26","cited_by_count":2,"area":null},{"id":"2305.16179","title":"Dropout Drops Double Descent","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2307.14253","title":"Sparse Double Descent in Vision Transformers: real or phantom threat?","created":"2023-07-26","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":"2409.20250","title":"Input-Label Correlation Governs a Linear-to-Nonlinear Transition in Random Features under Spiked Covariance","created":"2024-09-30","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":"2510.16208","title":"Explore-then-Commit for Nonstationary Linear Bandits with Latent Dynamics","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2208.13080","title":"Information FOMO: The unhealthy fear of missing out on information. A method for removing misleading data for healthier models","created":"2022-08-27","cited_by_count":1,"area":null},{"id":"2307.03176","title":"Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge Ensembles","created":"2023-07-06","cited_by_count":1,"area":null},{"id":"2311.11093","title":"Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2408.15784","title":"Implicit Regularization Paths of Weighted Neural Representations","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2409.15582","title":"Generalization vs. Specialization under Concept Shift","created":"2024-09-23","cited_by_count":1,"area":null},{"id":"2412.05418","title":"No Free Lunch From Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions","created":"2024-12-06","cited_by_count":1,"area":null},{"id":"2501.01376","title":"Deep P-Spline: Theory, Fast Tuning, and Application","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2509.14498","title":"Data coarse graining can improve model performance","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2605.18022","title":"Unveiling Memorization-Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2609.26392","title":"Double Descent and Malign Overfitting in Diffusion Models","created":"2026-09-22","cited_by_count":1,"area":"diffusion"},{"id":"2102.01194","title":"A Statistician Teaches Deep Learning","created":"2021-01-29","cited_by_count":0,"area":null},{"id":"2201.12803","title":"Generalizing similarity in noisy setups: the DIBS phenomenon","created":"2022-01-30","cited_by_count":0,"area":null},{"id":"2212.00433","title":"Regularization Trade-offs with Fake Features","created":"2022-12-01","cited_by_count":0,"area":null},{"id":"2302.07348","title":"Cliff-Learning","created":"2023-02-14","cited_by_count":0,"area":null},{"id":"2306.08432","title":"Batches Stabilize the Minimum Norm Risk in High Dimensional Overparameterized Linear Regression","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2308.16596","title":"The Quest of Finding the Antidote to Sparse Double Descent","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2312.01795","title":"Distributed Continual Learning with CoCoA in High-dimensional Linear Regression","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2312.03951","title":"Understanding the Role of Optimization in Double Descent","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2408.08294","title":"eGAD! double descent is explained by Generalized Aliasing Decomposition","created":"2024-08-15","cited_by_count":0,"area":null},{"id":"2412.07520","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","created":"2024-12-10","cited_by_count":0,"area":null},{"id":"2504.19351","title":"The Double Descent Behavior in Two Layer Neural Network for Binary Classification","created":"2025-04-27","cited_by_count":0,"area":null}],"next_cursor":"100"}