{"list":"other","total":57,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1905.02175","title":"Adversarial Examples Are Not Bugs, They Are Features","created":"2019-05-06","cited_by_count":953},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1902.06720","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","created":"2019-02-18","cited_by_count":738},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"1909.01377","title":"Deep Equilibrium Models","created":"2019-09-03","cited_by_count":615},{"id":"1710.08864","title":"One pixel attack for fooling deep neural networks","created":"2017-10-24","cited_by_count":582},{"id":"1405.4980","title":"Convex Optimization: Algorithms and Complexity","created":"2014-05-20","cited_by_count":575},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"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":"1407.0202","title":"SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives","created":"2014-07-01","cited_by_count":402},{"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":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"id":"2103.09177","title":"Deep learning: a statistical viewpoint","created":"2021-03-16","cited_by_count":240},{"id":"2003.00307","title":"Loss landscapes and optimization in over-parameterized non-linear systems and neural networks","created":"2020-02-29","cited_by_count":233},{"id":"1902.04742","title":"Uniform convergence may be unable to explain generalization in deep learning","created":"2019-02-13","cited_by_count":224},{"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":"1802.01396","title":"To understand deep learning we need to understand kernel learning","created":"2018-02-05","cited_by_count":187},{"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":"2007.15801","title":"Finite Versus Infinite Neural Networks: an Empirical Study","created":"2020-07-31","cited_by_count":157},{"id":"1712.06559","title":"The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning","created":"2017-12-18","cited_by_count":150},{"id":"2006.13409","title":"When Do Neural Networks Outperform Kernel Methods?","created":"2020-06-24","cited_by_count":150},{"id":"2006.07322","title":"Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks","created":"2020-06-12","cited_by_count":138},{"id":"1310.5715","title":"Stochastic Gradient Descent, Weighted Sampling, and the Randomized Kaczmarz algorithm","created":"2013-10-21","cited_by_count":133},{"id":"2010.01092","title":"On the linearity of large non-linear models: when and why the tangent kernel is constant","created":"2020-10-02","cited_by_count":129},{"id":"1903.09139","title":"Harmless interpolation of noisy data in regression","created":"2019-03-21","cited_by_count":121},{"id":"1605.07678","title":"An Analysis of Deep Neural Network Models for Practical Applications","created":"2016-05-24","cited_by_count":116},{"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":"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":"2006.10350","title":"Kernel methods through the roof: handling billions of points efficiently","created":"2020-06-18","cited_by_count":89},{"id":"1608.08967","title":"Robustness of classifiers: from adversarial to random noise","created":"2016-08-31","cited_by_count":88},{"id":"1812.10004","title":"Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?","created":"2018-12-25","cited_by_count":88},{"id":"1910.01663","title":"Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks","created":"2019-10-03","cited_by_count":87},{"id":"1810.09665","title":"A jamming transition from under- to over-parametrization affects loss landscape and generalization","created":"2018-10-22","cited_by_count":67},{"id":"2003.02237","title":"Neural Kernels Without Tangents","created":"2020-03-04","cited_by_count":56},{"id":"1504.07676","title":"Explaining the Success of AdaBoost and Random Forests as Interpolating Classifiers","created":"2015-04-28","cited_by_count":45},{"id":"1909.12362","title":"Overparameterized Neural Networks Implement Associative Memory","created":"2019-09-26","cited_by_count":45},{"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":"2004.04328","title":"A Brief Prehistory of Double Descent","created":"2020-04-07","cited_by_count":44},{"id":"1811.02564","title":"On exponential convergence of SGD in non-convex over-parametrized learning","created":"2018-11-06","cited_by_count":33},{"id":"2011.07729","title":"Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View","created":"2020-11-16","cited_by_count":32},{"id":"2010.08479","title":"Failures of model-dependent generalization bounds for least-norm interpolation","created":"2020-10-16","cited_by_count":26},{"id":"2006.05942","title":"On Uniform Convergence and Low-Norm Interpolation Learning","created":"2020-06-10","cited_by_count":24},{"id":"1906.03667","title":"Understanding overfitting peaks in generalization error: Analytical risk curves for $l_2$ and $l_1$ penalized interpolation","created":"2019-06-09","cited_by_count":23},{"id":"1905.13742","title":"High Dimensional Classification via Regularized and Unregularized Empirical Risk Minimization: Precise Error and Optimal Loss","created":"2019-05-31","cited_by_count":9},{"id":"1902.04782","title":"On the Expressive Power of Kernel Methods and the Efficiency of Kernel Learning by Association Schemes","created":"2019-02-13","cited_by_count":1}],"next_cursor":null}