{"total":187,"rows":[{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739,"area":null},{"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":"2205.15659","title":"The CLRS Algorithmic Reasoning Benchmark","created":"2022-05-31","cited_by_count":106,"area":null},{"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":"2206.04041","title":"Neural Collapse: A Review on Modelling Principles and Generalization","created":"2022-06-08","cited_by_count":95,"area":null},{"id":"2202.06526","title":"Benign Overfitting in Two-layer Convolutional Neural Networks","created":"2022-02-14","cited_by_count":91,"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":"2103.01550","title":"Label-Imbalanced and Group-Sensitive Classification under Overparameterization","created":"2021-03-02","cited_by_count":74,"area":null},{"id":"2302.05836","title":"Theory on Forgetting and Generalization of Continual Learning","created":"2023-02-12","cited_by_count":72,"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":"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":"2106.09276","title":"Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds, and Benign Overfitting","created":"2021-06-17","cited_by_count":54,"area":null},{"id":"2104.13628","title":"Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures","created":"2021-04-28","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":"2106.10865","title":"Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation","created":"2021-06-21","cited_by_count":42,"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":"2201.11489","title":"The Implicit Bias of Benign Overfitting","created":"2022-01-27","cited_by_count":38,"area":null},{"id":"2301.12832","title":"Deep networks for system identification: a Survey","created":"2023-01-30","cited_by_count":37,"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":"2106.05932","title":"Early-stopped neural networks are consistent","created":"2021-06-10","cited_by_count":34,"area":null},{"id":"2107.11228","title":"Taxonomizing local versus global structure in neural network loss landscapes","created":"2021-07-23","cited_by_count":34,"area":null},{"id":"2303.04145","title":"Benign Overfitting for Two-layer ReLU Convolutional Neural Networks","created":"2023-03-07","cited_by_count":34,"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":"2207.06475","title":"Analysis of Catastrophic Forgetting for Random Orthogonal Transformation Tasks in the Overparameterized Regime","created":"2022-06-01","cited_by_count":29,"area":null},{"id":"2303.01462","title":"Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization","created":"2023-03-02","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":"2112.03215","title":"Multi-scale Feature Learning Dynamics: Insights for Double Descent","created":"2021-12-06","cited_by_count":24,"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":"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":"2302.06210","title":"Precise Asymptotic Analysis of Deep Random Feature Models","created":"2023-02-13","cited_by_count":22,"area":null},{"id":"2203.14661","title":"Random matrix analysis of deep neural network weight matrices","created":"2022-03-28","cited_by_count":21,"area":null},{"id":"2204.06274","title":"Overparameterized Linear Regression under Adversarial Attacks","created":"2022-04-13","cited_by_count":21,"area":null},{"id":"2212.14457","title":"Bayesian Interpolation with Deep Linear Networks","created":"2022-12-29","cited_by_count":21,"area":null},{"id":"2310.10807","title":"Regularization properties of adversarially-trained linear regression","created":"2023-10-16","cited_by_count":18,"area":null},{"id":"2108.00131","title":"Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks","created":"2021-07-31","cited_by_count":17,"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":"2112.04470","title":"Optimistic Rates: A Unifying Theory for Interpolation Learning and Regularization in Linear Regression","created":"2021-12-08","cited_by_count":17,"area":null},{"id":"2305.15141","title":"From Tempered to Benign Overfitting in ReLU Neural Networks","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2106.07724","title":"An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks","created":"2021-06-14","cited_by_count":14,"area":null},{"id":"2111.05198","title":"Harmless interpolation in regression and classification with structured features","created":"2021-11-09","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":"2103.05243","title":"On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models","created":"2021-03-09","cited_by_count":13,"area":null},{"id":"2202.12780","title":"Model Comparison and Calibration Assessment: User Guide for Consistent Scoring Functions in Machine Learning and Actuarial Practice","created":"2022-02-25","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":"2212.13069","title":"Homophily modulates double descent generalization in graph convolution networks","created":"2022-12-26","cited_by_count":13,"area":null},{"id":"2106.15615","title":"A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning","created":"2021-06-29","cited_by_count":12,"area":null},{"id":"2206.07424","title":"Local Identifiability of Deep ReLU Neural Networks: the Theory","created":"2022-06-15","cited_by_count":12,"area":null},{"id":"2210.17449","title":"Globally Gated Deep Linear Networks","created":"2022-10-31","cited_by_count":12,"area":null},{"id":"2112.15250","title":"Benign Overfitting in Adversarially Robust Linear Classification","created":"2021-12-31","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":"2307.15396","title":"Noisy Interpolation Learning with Shallow Univariate ReLU Networks","created":"2023-07-28","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":"2408.16939","title":"Theoretical Insights into Overparameterized Models in Multi-Task and Replay-Based Continual Learning","created":"2024-08-29","cited_by_count":11,"area":null},{"id":"2505.17958","title":"The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks","created":"2025-05-23","cited_by_count":11,"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":"2310.01975","title":"Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data","created":"2023-10-03","cited_by_count":10,"area":null},{"id":"2112.04002","title":"SHRIMP: Sparser Random Feature Models via Iterative Magnitude Pruning","created":"2021-12-07","cited_by_count":9,"area":null},{"id":"2204.06935","title":"Concentration of Random Feature Matrices in High-Dimensions","created":"2022-04-14","cited_by_count":9,"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":"2401.12236","title":"The Surprising Harmfulness of Benign Overfitting for Adversarial Robustness","created":"2024-01-19","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":"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":"2105.14084","title":"Support vector machines and linear regression coincide with very high-dimensional features","created":"2021-05-28","cited_by_count":8,"area":null},{"id":"2206.01399","title":"Generalization for multiclass classification with overparameterized linear models","created":"2022-06-03","cited_by_count":8,"area":null},{"id":"2209.10080","title":"Deep Double Descent via Smooth Interpolation","created":"2022-09-21","cited_by_count":8,"area":null},{"id":"2406.09366","title":"Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations","created":"2024-06-13","cited_by_count":8,"area":null},{"id":"2509.09088","title":"An entropy formula for the Deep Linear Network","created":"2025-09-11","cited_by_count":8,"area":null},{"id":"2107.12685","title":"On the Role of Optimization in Double Descent: A Least Squares Study","created":"2021-07-27","cited_by_count":7,"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":"2203.05443","title":"Bias-variance decomposition of overparameterized regression with random linear features","created":"2022-03-10","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":"2403.17592","title":"On the Benefits of Over-parameterization for Out-of-Distribution Generalization","created":"2024-03-26","cited_by_count":7,"area":null},{"id":"2409.03891","title":"Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality","created":"2024-09-05","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":"2205.12510","title":"Exact Phase Transitions in Deep Learning","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2206.02047","title":"On the Generalization Power of the Overfitted Three-Layer Neural Tangent Kernel Model","created":"2022-06-04","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":"2310.00176","title":"Universality of max-margin classifiers","created":"2023-09-29","cited_by_count":6,"area":null},{"id":"2310.13572","title":"Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space","created":"2023-10-20","cited_by_count":6,"area":null},{"id":"2102.07238","title":"Double-descent curves in neural networks: a new perspective using Gaussian processes","created":"2021-02-14","cited_by_count":5,"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":"2106.15456","title":"A Mechanism for Producing Aligned Latent Spaces with Autoencoders","created":"2021-06-29","cited_by_count":5,"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":"2209.13394","title":"Magnitude and Angle Dynamics in Training Single ReLU Neurons","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2211.00227","title":"Transfer Learning with Kernel Methods","created":"2022-11-01","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":"2302.07828","title":"Over-parametrization via Lifting for Low-rank Matrix Sensing: Conversion of Spurious Solutions to Strict Saddle Points","created":"2023-02-15","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":"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":"2101.09001","title":"Linear Regression with Distributed Learning: A Generalization Error Perspective","created":"2021-01-22","cited_by_count":4,"area":null},{"id":"2103.14108","title":"The Geometry of Over-parameterized Regression and Adversarial Perturbations","created":"2021-03-25","cited_by_count":4,"area":null},{"id":"2106.01714","title":"Optimization Variance: Exploring Generalization Properties of DNNs","created":"2021-06-03","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":"2205.15549","title":"VC Theoretical Explanation of Double Descent","created":"2022-05-31","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":"2302.00257","title":"Implicit Regularization Leads to Benign Overfitting for Sparse Linear Regression","created":"2023-02-01","cited_by_count":4,"area":null},{"id":"2303.07475","title":"General Loss Functions Lead to (Approximate) Interpolation in High Dimensions","created":"2023-03-13","cited_by_count":4,"area":null}],"next_cursor":"100"}