{"list":"other","total":52,"rows":[{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"id":"1903.08560","title":"Surprises in High-Dimensional Ridgeless Least Squares Interpolation","created":"2019-03-19","cited_by_count":513},{"id":"1908.05355","title":"The generalization error of random features regression: Precise asymptotics and double descent curve","created":"2019-08-14","cited_by_count":413},{"id":"1906.05890","title":"Gradient Descent Maximizes the Margin of Homogeneous Neural Networks","created":"2019-06-13","cited_by_count":320},{"id":"2002.04486","title":"Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss","created":"2020-02-11","cited_by_count":268},{"id":"1802.08246","title":"Characterizing Implicit Bias in Terms of Optimization Geometry","created":"2018-02-22","cited_by_count":266},{"id":"1903.07571","title":"Two models of double descent for weak features","created":"2019-03-18","cited_by_count":195},{"id":"1808.00387","title":"Just Interpolate: Kernel \"Ridgeless\" Regression Can Generalize","created":"2018-08-01","cited_by_count":190},{"id":"2006.06657","title":"Directional convergence and alignment in deep learning","created":"2020-06-11","cited_by_count":178},{"id":"2009.14286","title":"Benign overfitting in ridge regression","created":"2020-09-29","cited_by_count":153},{"id":"1903.09139","title":"Harmless interpolation of noisy data in regression","created":"2019-03-21","cited_by_count":121},{"id":"1803.01905","title":"Convergence of Gradient Descent on Separable Data","created":"2018-03-05","cited_by_count":110},{"id":"1806.05161","title":"Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate","created":"2018-06-13","cited_by_count":99},{"id":"2006.05800","title":"On the Optimal Weighted $\\ell_2$ Regularization in Overparameterized Linear Regression","created":"2020-06-10","cited_by_count":98},{"id":"2005.08054","title":"Classification vs regression in overparameterized regimes: Does the loss function matter?","created":"2020-05-16","cited_by_count":97},{"id":"2202.06526","title":"Benign Overfitting in Two-layer Convolutional Neural Networks","created":"2022-02-14","cited_by_count":91},{"id":"2208.12591","title":"On the Implicit Bias in Deep-Learning Algorithms","created":"2022-08-26","cited_by_count":86},{"id":"1803.07300","title":"Risk and parameter convergence of logistic regression","created":"2018-03-20","cited_by_count":85},{"id":"2110.13905","title":"Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias","created":"2021-10-26","cited_by_count":83},{"id":"2004.12019","title":"Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime","created":"2020-04-25","cited_by_count":81},{"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},{"id":"1806.01796","title":"Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate","created":"2018-06-05","cited_by_count":64},{"id":"2006.11226","title":"Gradient descent follows the regularization path for general losses","created":"2020-06-19","cited_by_count":59},{"id":"2106.09276","title":"Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds, and Benign Overfitting","created":"2021-06-17","cited_by_count":54},{"id":"2201.12760","title":"Implicit Regularization Towards Rank Minimization in ReLU Networks","created":"2022-01-30","cited_by_count":53},{"id":"2104.13628","title":"Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures","created":"2021-04-28","cited_by_count":49},{"id":"2210.07082","title":"Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data","created":"2022-10-13","cited_by_count":46},{"id":"1812.11167","title":"Consistency of Interpolation with Laplace Kernels is a High-Dimensional Phenomenon","created":"2018-12-28","cited_by_count":44},{"id":"1912.04265","title":"In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors","created":"2019-12-09","cited_by_count":44},{"id":"2106.10865","title":"Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation","created":"2021-06-21","cited_by_count":42},{"id":"2201.11489","title":"The Implicit Bias of Benign Overfitting","created":"2022-01-27","cited_by_count":38},{"id":"2207.06569","title":"Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting","created":"2022-07-14","cited_by_count":36},{"id":"2110.02732","title":"On Margin Maximization in Linear and ReLU Networks","created":"2021-10-06","cited_by_count":34},{"id":"2107.00595","title":"Fast Margin Maximization via Dual Acceleration","created":"2021-07-01","cited_by_count":33},{"id":"2009.10670","title":"On the proliferation of support vectors in high dimensions","created":"2020-09-22","cited_by_count":32},{"id":"2011.07729","title":"Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View","created":"2020-11-16","cited_by_count":32},{"id":"2007.00028","title":"Gradient Methods Never Overfit On Separable Data","created":"2020-06-30","cited_by_count":29},{"id":"2011.09148","title":"Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting and Regularization","created":"2020-11-18","cited_by_count":27},{"id":"2202.04347","title":"Gradient Methods Provably Converge to Non-Robust Networks","created":"2022-02-09","cited_by_count":27},{"id":"2010.08479","title":"Failures of model-dependent generalization bounds for least-norm interpolation","created":"2020-10-16","cited_by_count":26},{"id":"2210.03820","title":"The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks","created":"2022-10-07","cited_by_count":25},{"id":"2101.11815","title":"Interpolating Classifiers Make Few Mistakes","created":"2021-01-28","cited_by_count":22},{"id":"2203.03597","title":"Fast Rates for Noisy Interpolation Require Rethinking the Effects of Inductive Bias","created":"2022-03-07","cited_by_count":22},{"id":"2205.09072","title":"On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias","created":"2022-05-18","cited_by_count":21},{"id":"2101.02533","title":"Towards Understanding Learning in Neural Networks with Linear Teachers","created":"2021-01-07","cited_by_count":19},{"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},{"id":"2101.01152","title":"Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise","created":"2021-01-04","cited_by_count":17},{"id":"2111.05987","title":"Tight bounds for minimum l1-norm interpolation of noisy data","created":"2021-11-10","cited_by_count":16},{"id":"2010.00539","title":"Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins","created":"2020-10-01","cited_by_count":14},{"id":"2111.05198","title":"Harmless interpolation in regression and classification with structured features","created":"2021-11-09","cited_by_count":14}],"next_cursor":null}