{"total":117,"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":"2202.05928","title":"Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data","created":"2022-02-11","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":"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":"2203.08124","title":"Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective","created":"2022-03-15","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":"2106.10865","title":"Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation","created":"2021-06-21","cited_by_count":42,"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":"2107.11228","title":"Taxonomizing local versus global structure in neural network loss landscapes","created":"2021-07-23","cited_by_count":34,"area":null},{"id":"2402.05738","title":"Implicit Bias and Fast Convergence Rates for Self-attention","created":"2024-02-08","cited_by_count":31,"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":"2108.05574","title":"Implicit Sparse Regularization: The Impact of Depth and Early Stopping","created":"2021-08-12","cited_by_count":30,"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":"2110.02914","title":"Foolish Crowds Support Benign Overfitting","created":"2021-10-06","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":"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":"2201.06142","title":"Towards Sample-efficient Overparameterized Meta-learning","created":"2022-01-16","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":"2412.07684","title":"The Pitfalls of Memorization: When Memorization Hurts Generalization","created":"2024-12-10","cited_by_count":19,"area":null},{"id":"2108.11489","title":"The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks","created":"2021-08-25","cited_by_count":18,"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":"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":"2111.05987","title":"Tight bounds for minimum l1-norm interpolation of noisy data","created":"2021-11-10","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":"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":"2205.13525","title":"On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions","created":"2022-05-26","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":"2210.12082","title":"A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models","created":"2022-10-21","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":"2309.04268","title":"Optimal Rate of Kernel Regression in Large Dimensions","created":"2023-09-08","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":"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":"2501.10077","title":"Double descent in quantum kernel methods","created":"2025-01-17","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":"2209.09315","title":"Deep Linear Networks can Benignly Overfit when Shallow Ones Do","created":"2022-09-19","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":"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":"2306.09955","title":"Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign?","created":"2023-06-16","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":"2502.20032","title":"Order-Robust Class Incremental Learning: Graph-Driven Dynamic Similarity Grouping","created":"2025-02-27","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":"2206.07892","title":"Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence","created":"2022-06-16","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":"2403.06903","title":"Benign overfitting in leaky ReLU networks with moderate input dimension","created":"2024-03-11","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":"2206.00501","title":"Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2306.13185","title":"An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression","created":"2023-06-22","cited_by_count":5,"area":null},{"id":"2409.18842","title":"Classical Statistical (In-Sample) Intuitions Don't Generalize Well: A Note on Bias-Variance Tradeoffs, Overfitting and Moving from Fixed to Random Designs","created":"2024-09-27","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":"2111.14039","title":"Generalization Performance of Empirical Risk Minimization on Over-parameterized Deep ReLU Nets","created":"2021-11-28","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":"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},{"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":"2305.14689","title":"Least Squares Regression Can Exhibit Under-Parameterized Double Descent","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2306.04901","title":"Generalization Performance of Transfer Learning: Overparameterized and Underparameterized Regimes","created":"2023-06-08","cited_by_count":4,"area":null},{"id":"2411.13733","title":"On Generalization Bounds for Neural Networks with Low Rank Layers","created":"2024-11-20","cited_by_count":4,"area":null},{"id":"2502.10442","title":"Analysis of Overparameterization in Continual Learning under a Linear Model","created":"2025-02-11","cited_by_count":4,"area":null},{"id":"2106.04794","title":"Towards the Memorization Effect of Neural Networks in Adversarial Training","created":"2021-06-09","cited_by_count":3,"area":null},{"id":"2107.00797","title":"Mitigating deep double descent by concatenating inputs","created":"2021-07-02","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":"2112.07344","title":"SCORE: Approximating Curvature Information under Self-Concordant Regularization","created":"2021-12-14","cited_by_count":3,"area":null},{"id":"2204.02678","title":"Random Features Model with General Convex Regularization: A Fine Grained Analysis with Precise Asymptotic Learning Curves","created":"2022-04-06","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":"2305.02304","title":"New Equivalences Between Interpolation and SVMs: Kernels and Structured Features","created":"2023-05-03","cited_by_count":3,"area":null},{"id":"2306.13255","title":"Precise Asymptotic Generalization for Multiclass Classification with Overparameterized Linear Models","created":"2023-06-23","cited_by_count":3,"area":null},{"id":"2409.17328","title":"The poison of dimensionality","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2510.15337","title":"Transfer Learning for Benign Overfitting in High-Dimensional Linear Regression","created":"2025-10-17","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":"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":"2203.03398","title":"Estimation under Model Misspecification with Fake Features","created":"2022-03-07","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":"2503.17020","title":"Benign Overfitting with Quantum Kernels","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2106.02100","title":"Double Descent Optimization Pattern and Aliasing: Caveats of Noisy Labels","created":"2021-06-03","cited_by_count":1,"area":null},{"id":"2109.13215","title":"Classification and Adversarial examples in an Overparameterized Linear Model: A Signal Processing Perspective","created":"2021-09-27","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},{"id":"2506.17187","title":"Optimal Implicit Bias in Linear Regression","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2509.21181","title":"Closed-form $\\ell_r$ norm scaling with data for overparameterized linear regression and diagonal linear networks under $\\ell_p$ bias","created":"2025-09-25","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":"2602.00825","title":"Harmful Overfitting in Sobolev Spaces","created":"2026-01-31","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":"2605.21402","title":"Memorisation, convergence and generalisation in generative models","created":"2026-05-20","cited_by_count":1,"area":null}],"next_cursor":"100"}