{"list":"other","total":75,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"1904.12848","title":"Unsupervised Data Augmentation for Consistency Training","created":"2019-04-29","cited_by_count":1060},{"id":"1804.06872","title":"Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels","created":"2018-04-18","cited_by_count":1059},{"id":"1805.07836","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","created":"2018-05-20","cited_by_count":997},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"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":"2002.07394","title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","created":"2020-02-18","cited_by_count":692},{"id":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"1609.03683","title":"Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach","created":"2016-09-13","cited_by_count":665},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"1603.00943","title":"CVXPY: A Python-Embedded Modeling Language for Convex Optimization","created":"2016-03-03","cited_by_count":641},{"id":"2007.08199","title":"Learning from Noisy Labels with Deep Neural Networks: A Survey","created":"2020-07-16","cited_by_count":582},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"1908.06112","title":"Symmetric Cross Entropy for Robust Learning with Noisy Labels","created":"2019-08-16","cited_by_count":500},{"id":"1712.09482","title":"Robust Loss Functions under Label Noise for Deep Neural Networks","created":"2017-12-27","cited_by_count":443},{"id":"2007.00151","title":"Early-Learning Regularization Prevents Memorization of Noisy Labels","created":"2020-06-30","cited_by_count":416},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1412.6614","title":"In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning","created":"2014-12-20","cited_by_count":342},{"id":"1412.6596","title":"Training Deep Neural Networks on Noisy Labels with Bootstrapping","created":"2014-12-20","cited_by_count":322},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"id":"1803.11364","title":"Joint Optimization Framework for Learning with Noisy Labels","created":"2018-03-30","cited_by_count":293},{"id":"1708.02862","title":"WebVision Database: Visual Learning and Understanding from Web Data","created":"2017-08-09","cited_by_count":262},{"id":"2006.13554","title":"Normalized Loss Functions for Deep Learning with Noisy Labels","created":"2020-06-24","cited_by_count":257},{"id":"2110.12088","title":"Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations","created":"2021-10-22","cited_by_count":256},{"id":"1503.02101","title":"Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition","created":"2015-03-06","cited_by_count":243},{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227},{"id":"1802.05300","title":"Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise","created":"2018-02-14","cited_by_count":216},{"id":"1906.00189","title":"Are Anchor Points Really Indispensable in Label-Noise Learning?","created":"2019-06-01","cited_by_count":208},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"2003.02819","title":"Does label smoothing mitigate label noise?","created":"2020-03-05","cited_by_count":204},{"id":"1806.02612","title":"Dimensionality-Driven Learning with Noisy Labels","created":"2018-06-07","cited_by_count":173},{"id":"2101.12699","title":"Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training","created":"2021-01-29","cited_by_count":166},{"id":"1809.09573","title":"Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview","created":"2018-09-25","cited_by_count":160},{"id":"1812.05214","title":"Learning to Learn from Noisy Labeled Data","created":"2018-12-13","cited_by_count":160},{"id":"1903.11680","title":"Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks","created":"2019-03-27","cited_by_count":159},{"id":"2010.02347","title":"Learning with Instance-Dependent Label Noise: A Sample Sieve Approach","created":"2020-10-05","cited_by_count":158},{"id":"2106.02073","title":"Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path","created":"2021-06-03","cited_by_count":158},{"id":"2012.09839","title":"Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning","created":"2020-12-17","cited_by_count":150},{"id":"1704.07433","title":"Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples","created":"2017-04-24","cited_by_count":147},{"id":"2006.08558","title":"Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction","created":"2020-06-15","cited_by_count":142},{"id":"2002.10319","title":"Self-Adaptive Training: beyond Empirical Risk Minimization","created":"2020-02-24","cited_by_count":126},{"id":"2005.06398","title":"Implicit Regularization in Deep Learning May Not Be Explainable by Norms","created":"2020-05-13","cited_by_count":119},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110},{"id":"2002.11328","title":"Rethinking Bias-Variance Trade-off for Generalization of Neural Networks","created":"2020-02-26","cited_by_count":107},{"id":"1912.05170","title":"Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey","created":"2019-12-11","cited_by_count":101},{"id":"2102.02400","title":"Provably End-to-end Label-Noise Learning without Anchor Points","created":"2021-02-04","cited_by_count":97},{"id":"1505.01554","title":"Webly Supervised Learning of Convolutional Networks","created":"2015-05-07","cited_by_count":95},{"id":"1812.10004","title":"Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?","created":"2018-12-25","cited_by_count":88},{"id":"2105.10446","title":"ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction","created":"2021-05-21","cited_by_count":84},{"id":"2102.11628","title":"FINE Samples for Learning with Noisy Labels","created":"2021-02-23","cited_by_count":82},{"id":"1909.05122","title":"Implicit Regularization for Optimal Sparse Recovery","created":"2019-09-11","cited_by_count":80},{"id":"2106.15013","title":"Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction","created":"2021-06-28","cited_by_count":78},{"id":"2011.10077","title":"Error-Bounded Correction of Noisy Labels","created":"2020-11-19","cited_by_count":74},{"id":"1906.05392","title":"Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian","created":"2019-06-12","cited_by_count":67},{"id":"2102.05291","title":"Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels","created":"2021-02-10","cited_by_count":65},{"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":"2102.02414","title":"Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization","created":"2021-02-04","cited_by_count":62},{"id":"2110.03740","title":"Adaptive Early-Learning Correction for Segmentation from Noisy Annotations","created":"2021-10-07","cited_by_count":62},{"id":"1906.03361","title":"Robust Bi-Tempered Logistic Loss Based on Bregman Divergences","created":"2019-06-08","cited_by_count":61},{"id":"2006.11226","title":"Gradient descent follows the regularization path for general losses","created":"2020-06-19","cited_by_count":59},{"id":"2011.03687","title":"When Optimizing $f$-divergence is Robust with Label Noise","created":"2020-11-07","cited_by_count":44},{"id":"1911.08059","title":"How does Early Stopping Help Generalization against Label Noise?","created":"2019-11-19","cited_by_count":41},{"id":"2202.09844","title":"Sparsity Winning Twice: Better Robust Generalization from More Efficient Training","created":"2022-02-20","cited_by_count":41},{"id":"2108.05574","title":"Implicit Sparse Regularization: The Impact of Depth and Early Stopping","created":"2021-08-12","cited_by_count":30},{"id":"2006.08857","title":"Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization","created":"2020-06-16","cited_by_count":26},{"id":"2112.11027","title":"More is Less: Inducing Sparsity via Overparameterization","created":"2021-12-21","cited_by_count":24},{"id":"2109.11154","title":"Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery","created":"2021-09-23","cited_by_count":22},{"id":"2102.00751","title":"Learning to Combat Noisy Labels via Classification Margins","created":"2021-02-01","cited_by_count":4},{"id":"2112.08102","title":"Robust Neural Network Classification via Double Regularization","created":"2021-12-15","cited_by_count":1}],"next_cursor":null}