{"list":"other","total":52,"rows":[{"id":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"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":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"1906.05890","title":"Gradient Descent Maximizes the Margin of Homogeneous Neural Networks","created":"2019-06-13","cited_by_count":320},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"id":"1802.08246","title":"Characterizing Implicit Bias in Terms of Optimization Geometry","created":"2018-02-22","cited_by_count":266},{"id":"1810.02032","title":"Gradient descent aligns the layers of deep linear networks","created":"2018-10-04","cited_by_count":182},{"id":"2009.14286","title":"Benign overfitting in ridge regression","created":"2020-09-29","cited_by_count":153},{"id":"1803.01905","title":"Convergence of Gradient Descent on Separable Data","created":"2018-03-05","cited_by_count":110},{"id":"2005.08054","title":"Classification vs regression in overparameterized regimes: Does the loss function matter?","created":"2020-05-16","cited_by_count":97},{"id":"1803.07300","title":"Risk and parameter convergence of logistic regression","created":"2018-03-20","cited_by_count":85},{"id":"2106.15933","title":"Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity","created":"2021-06-30","cited_by_count":85},{"id":"2004.12019","title":"Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime","created":"2020-04-25","cited_by_count":81},{"id":"1909.05122","title":"Implicit Regularization for Optimal Sparse Recovery","created":"2019-09-11","cited_by_count":80},{"id":"2007.06738","title":"Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy","created":"2020-07-13","cited_by_count":71},{"id":"1810.10082","title":"A Continuous-Time View of Early Stopping for Least Squares","created":"2018-10-23","cited_by_count":69},{"id":"1909.12051","title":"The Implicit Bias of Depth: How Incremental Learning Drives Generalization","created":"2019-09-26","cited_by_count":64},{"id":"2304.00488","title":"Saddle-to-Saddle Dynamics in Diagonal Linear Networks","created":"2023-04-02","cited_by_count":57},{"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":"2110.06198","title":"Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression","created":"2021-10-12","cited_by_count":38},{"id":"2201.11489","title":"The Implicit Bias of Benign Overfitting","created":"2022-01-27","cited_by_count":38},{"id":"2302.08982","title":"(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability","created":"2023-02-17","cited_by_count":36},{"id":"2010.08515","title":"Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?","created":"2020-10-16","cited_by_count":34},{"id":"1303.6149","title":"Adaptivity of averaged stochastic gradient descent to local strong convexity for logistic regression","created":"2013-03-25","cited_by_count":32},{"id":"2108.04552","title":"The Benefits of Implicit Regularization from SGD in Least Squares Problems","created":"2021-08-10","cited_by_count":32},{"id":"1810.06838","title":"Finite-sample analysis of M-estimators using self-concordance","created":"2018-10-16","cited_by_count":30},{"id":"1902.03046","title":"Beyond Least-Squares: Fast Rates for Regularized Empirical Risk Minimization through Self-Concordance","created":"2019-02-08","cited_by_count":28},{"id":"1911.01544","title":"The generalization error of max-margin linear classifiers: Benign overfitting and high dimensional asymptotics in the overparametrized regime","created":"2019-11-05","cited_by_count":28},{"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":"2508.03688","title":"Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws","created":"2025-08-05","cited_by_count":25},{"id":"2105.08368","title":"Convergence Rates of Gradient Methods for Convex Optimization in the Space of Measures","created":"2021-05-18","cited_by_count":20},{"id":"2002.00189","title":"The Statistical Complexity of Early-Stopped Mirror Descent","created":"2020-02-01","cited_by_count":19},{"id":"2410.22069","title":"Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks","created":"2024-10-29","cited_by_count":18},{"id":"2104.01493","title":"Exponentiated Gradient Reweighting for Robust Training Under Label Noise and Beyond","created":"2021-04-03","cited_by_count":16},{"id":"2106.01429","title":"Smooth Bilevel Programming for Sparse Regularization","created":"2021-06-02","cited_by_count":14},{"id":"2306.13853","title":"A Unified Approach to Controlling Implicit Regularization via Mirror Descent","created":"2023-06-24","cited_by_count":14},{"id":"2307.04191","title":"On the sample complexity of parameter estimation in logistic regression with normal design","created":"2023-07-09","cited_by_count":13},{"id":"2410.04489","title":"Grokking at the Edge of Linear Separability","created":"2024-10-06","cited_by_count":12},{"id":"2002.02950","title":"Logistic Regression Regret: What's the Catch?","created":"2020-02-07","cited_by_count":10},{"id":"2406.12763","title":"Implicit Bias of Mirror Flow on Separable Data","created":"2024-06-18","cited_by_count":9},{"id":"2502.13283","title":"Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression","created":"2025-02-18","cited_by_count":9},{"id":"2502.16075","title":"Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks","created":"2025-02-22","cited_by_count":9},{"id":"2509.17251","title":"Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization","created":"2025-09-21","cited_by_count":8},{"id":"2202.00145","title":"Step-size Adaptation Using Exponentiated Gradient Updates","created":"2022-01-31","cited_by_count":7},{"id":"2311.14222","title":"Risk Bounds of Accelerated SGD for Overparameterized Linear Regression","created":"2023-11-23","cited_by_count":7},{"id":"2411.02137","title":"Finite-sample performance of the maximum likelihood estimator in logistic regression","created":"2024-11-04","cited_by_count":7},{"id":"2502.20531","title":"Learning Dynamics of Deep Linear Networks Beyond the Edge of Stability","created":"2025-02-27","cited_by_count":5},{"id":"2302.00257","title":"Implicit Regularization Leads to Benign Overfitting for Sparse Linear Regression","created":"2023-02-01","cited_by_count":4},{"id":"2502.18393","title":"Learning sparse generalized linear models with binary outcomes via iterative hard thresholding","created":"2025-02-25","cited_by_count":4},{"id":"2503.07966","title":"Benign Overfitting and the Geometry of the Ridge Regression Solution in Binary Classification","created":"2025-03-11","cited_by_count":2},{"id":"2512.24999","title":"Basic Inequalities for First-Order Optimization with Applications to Statistical Risk Analysis","created":"2025-12-31","cited_by_count":2}],"next_cursor":null}