{"list":"other","total":73,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"1603.06560","title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","created":"2016-03-21","cited_by_count":699},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"id":"1609.05807","title":"Inherent Trade-Offs in the Fair Determination of Risk Scores","created":"2016-09-19","cited_by_count":586},{"id":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"id":"1710.05381","title":"A systematic study of the class imbalance problem in convolutional neural networks","created":"2017-10-15","cited_by_count":513},{"id":"1804.06561","title":"A Mean Field View of the Landscape of Two-Layers Neural Networks","created":"2018-04-18","cited_by_count":466},{"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":"1912.02413","title":"BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition","created":"2019-12-05","cited_by_count":403},{"id":"1610.08452","title":"Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment","created":"2016-10-26","cited_by_count":369},{"id":"2006.09994","title":"Noise or Signal: The Role of Image Backgrounds in Object Recognition","created":"2020-06-17","cited_by_count":343},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"2003.05176","title":"Equalization Loss for Long-Tailed Object Recognition","created":"2020-03-11","cited_by_count":285},{"id":"1801.05599","title":"Additive Margin Softmax for Face Verification","created":"2018-01-17","cited_by_count":278},{"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":"1806.00468","title":"Implicit Bias of Gradient Descent on Linear Convolutional Networks","created":"2018-06-01","cited_by_count":251},{"id":"1812.03372","title":"What is the Effect of Importance Weighting in Deep Learning?","created":"2018-12-08","cited_by_count":251},{"id":"1802.08626","title":"Empirical Risk Minimization under Fairness Constraints","created":"2018-02-23","cited_by_count":226},{"id":"1903.07571","title":"Two models of double descent for weak features","created":"2019-03-18","cited_by_count":195},{"id":"1802.01396","title":"To understand deep learning we need to understand kernel learning","created":"2018-02-05","cited_by_count":187},{"id":"1508.03422","title":"Cost Sensitive Learning of Deep Feature Representations from Imbalanced Data","created":"2015-08-14","cited_by_count":167},{"id":"1909.02060","title":"Distributionally Robust Language Modeling","created":"2019-09-04","cited_by_count":143},{"id":"2011.11619","title":"Neural collapse with unconstrained features","created":"2020-11-23","cited_by_count":142},{"id":"1803.01905","title":"Convergence of Gradient Descent on Separable Data","created":"2018-03-05","cited_by_count":110},{"id":"1811.10104","title":"50 Years of Test (Un)fairness: Lessons for Machine Learning","created":"2018-11-25","cited_by_count":101},{"id":"2005.08054","title":"Classification vs regression in overparameterized regimes: Does the loss function matter?","created":"2020-05-16","cited_by_count":97},{"id":"1806.09471","title":"Does data interpolation contradict statistical optimality?","created":"2018-06-25","cited_by_count":95},{"id":"1306.3574","title":"Early stopping and non-parametric regression: An optimal data-dependent stopping rule","created":"2013-06-15","cited_by_count":89},{"id":"1812.10004","title":"Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?","created":"2018-12-25","cited_by_count":88},{"id":"1803.07300","title":"Risk and parameter convergence of logistic regression","created":"2018-03-20","cited_by_count":85},{"id":"1901.08665","title":"Fairness risk measures","created":"2019-01-24","cited_by_count":85},{"id":"1803.06964","title":"A modern maximum-likelihood theory for high-dimensional logistic regression","created":"2018-03-19","cited_by_count":81},{"id":"1911.05822","title":"A Model of Double Descent for High-dimensional Binary Linear Classification","created":"2019-11-13","cited_by_count":81},{"id":"2001.01385","title":"Identifying and Compensating for Feature Deviation in Imbalanced Deep Learning","created":"2020-01-06","cited_by_count":76},{"id":"1810.10082","title":"A Continuous-Time View of Early Stopping for Least Squares","created":"2018-10-23","cited_by_count":69},{"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":"2002.11544","title":"The role of regularization in classification of high-dimensional noisy Gaussian mixture","created":"2020-02-26","cited_by_count":63},{"id":"2006.11226","title":"Gradient descent follows the regularization path for general losses","created":"2020-06-19","cited_by_count":59},{"id":"1601.05150","title":"Factors in Finetuning Deep Model for object detection","created":"2016-01-20","cited_by_count":53},{"id":"1912.01857","title":"Adjusting Decision Boundary for Class Imbalanced Learning","created":"2019-12-04","cited_by_count":52},{"id":"2012.08465","title":"Neural Collapse with Cross-Entropy Loss","created":"2020-12-15","cited_by_count":52},{"id":"2006.06560","title":"Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization","created":"2020-06-11","cited_by_count":51},{"id":"1804.09753","title":"The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regression","created":"2018-04-25","cited_by_count":46},{"id":"2002.01586","title":"A Precise High-Dimensional Asymptotic Theory for Boosting and Minimum-$\\ell_1$-Norm Interpolated Classifiers","created":"2020-02-05","cited_by_count":44},{"id":"1303.7291","title":"A framework to characterize performance of LASSO algorithms","created":"2013-03-29","cited_by_count":40},{"id":"2012.08749","title":"Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks","created":"2020-12-16","cited_by_count":40},{"id":"1611.02041","title":"Does Distributionally Robust Supervised Learning Give Robust Classifiers?","created":"2016-11-07","cited_by_count":38},{"id":"1906.03761","title":"The Impact of Regularization on High-dimensional Logistic Regression","created":"2019-06-10","cited_by_count":35},{"id":"1806.00952","title":"Stochastic Gradient/Mirror Descent: Minimax Optimality and Implicit Regularization","created":"2018-06-04","cited_by_count":29},{"id":"2001.11572","title":"Analytic Study of Double Descent in Binary Classification: The Impact of Loss","created":"2020-01-30","cited_by_count":28},{"id":"2005.00180","title":"Generalization Error of Generalized Linear Models in High Dimensions","created":"2020-05-01","cited_by_count":25},{"id":"1511.09433","title":"Universality laws for randomized dimension reduction, with applications","created":"2015-11-30","cited_by_count":21},{"id":"1606.01800","title":"Finite Sample Analysis of Approximate Message Passing Algorithms","created":"2016-06-06","cited_by_count":20},{"id":"1311.0830","title":"The Squared-Error of Generalized LASSO: A Precise Analysis","created":"2013-11-04","cited_by_count":15},{"id":"1303.7289","title":"Upper-bounding $\\ell_1$-optimization weak thresholds","created":"2013-03-29","cited_by_count":14},{"id":"2002.07284","title":"Sharp Asymptotics and Optimal Performance for Inference in Binary Models","created":"2020-02-17","cited_by_count":13},{"id":"2006.08917","title":"Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions","created":"2020-06-16","cited_by_count":13},{"id":"1710.05895","title":"Spectral Algorithms for Computing Fair Support Vector Machines","created":"2017-10-16","cited_by_count":9},{"id":"1909.09345","title":"Does SLOPE outperform bridge regression?","created":"2019-09-20","cited_by_count":8},{"id":"2002.09831","title":"On the Role of Dataset Quality and Heterogeneity in Model Confidence","created":"2020-02-23","cited_by_count":7},{"id":"1304.0002","title":"A performance analysis framework for SOCP algorithms in noisy compressed sensing","created":"2013-03-29","cited_by_count":4},{"id":"1711.11215","title":"Symbol Error Rate Performance of Box-relaxation Decoders in Massive MIMO","created":"2017-11-30","cited_by_count":4}],"next_cursor":null}