{"list":"other","total":63,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"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":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"2007.08199","title":"Learning from Noisy Labels with Deep Neural Networks: A Survey","created":"2020-07-16","cited_by_count":582},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"id":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1903.08560","title":"Surprises in High-Dimensional Ridgeless Least Squares Interpolation","created":"2019-03-19","cited_by_count":513},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"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":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"1707.09564","title":"A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks","created":"2017-07-29","cited_by_count":314},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"1712.06541","title":"Size-Independent Sample Complexity of Neural Networks","created":"2017-12-18","cited_by_count":290},{"id":"1808.01204","title":"Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data","created":"2018-08-03","cited_by_count":261},{"id":"1902.04742","title":"Uniform convergence may be unable to explain generalization in deep learning","created":"2019-02-13","cited_by_count":224},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"1811.03600","title":"Measuring the Effects of Data Parallelism on Neural Network Training","created":"2018-11-08","cited_by_count":193},{"id":"1802.01396","title":"To understand deep learning we need to understand kernel learning","created":"2018-02-05","cited_by_count":187},{"id":"1805.08522","title":"Deep learning generalizes because the parameter-function map is biased towards simple functions","created":"2018-05-22","cited_by_count":183},{"id":"1705.10694","title":"Deep Learning is Robust to Massive Label Noise","created":"2017-05-30","cited_by_count":165},{"id":"2002.09572","title":"The Break-Even Point on Optimization Trajectories of Deep Neural Networks","created":"2020-02-21","cited_by_count":150},{"id":"1805.12076","title":"Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks","created":"2018-05-30","cited_by_count":142},{"id":"1811.08888","title":"Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks","created":"2018-11-21","cited_by_count":141},{"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":"1804.05862","title":"Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach","created":"2018-04-16","cited_by_count":126},{"id":"2010.05627","title":"Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning","created":"2020-10-12","cited_by_count":126},{"id":"1703.01678","title":"Data-Dependent Stability of Stochastic Gradient Descent","created":"2017-03-05","cited_by_count":92},{"id":"1902.00744","title":"Asymmetric Valleys: Beyond Sharp and Flat Local Minima","created":"2019-02-02","cited_by_count":90},{"id":"2110.09485","title":"Learning in High Dimension Always Amounts to Extrapolation","created":"2021-10-18","cited_by_count":66},{"id":"2012.14193","title":"Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization","created":"2020-12-28","cited_by_count":62},{"id":"1902.00621","title":"On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex Learning","created":"2019-02-02","cited_by_count":57},{"id":"2012.00152","title":"Every Model Learned by Gradient Descent Is Approximately a Kernel Machine","created":"2020-11-30","cited_by_count":55},{"id":"1905.13344","title":"Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience","created":"2019-05-30","cited_by_count":51},{"id":"1906.02613","title":"Bad Global Minima Exist and SGD Can Reach Them","created":"2019-06-06","cited_by_count":49},{"id":"1901.09491","title":"Stiffness: A New Perspective on Generalization in Neural Networks","created":"2019-01-28","cited_by_count":46},{"id":"1904.06963","title":"The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent","created":"2019-04-15","cited_by_count":46},{"id":"2010.13988","title":"Toward Better Generalization Bounds with Locally Elastic Stability","created":"2020-10-27","cited_by_count":42},{"id":"2002.10657","title":"Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization","created":"2020-02-25","cited_by_count":41},{"id":"2001.07384","title":"Understanding Why Neural Networks Generalize Well Through GSNR of Parameters","created":"2020-01-21","cited_by_count":40},{"id":"1910.06943","title":"The Local Elasticity of Neural Networks","created":"2019-10-15","cited_by_count":37},{"id":"2004.13336","title":"Automatic Cross-Replica Sharding of Weight Update in Data-Parallel Training","created":"2020-04-28","cited_by_count":30},{"id":"2008.13363","title":"Extreme Memorization via Scale of Initialization","created":"2020-08-31","cited_by_count":18},{"id":"2010.11775","title":"Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity","created":"2020-10-22","cited_by_count":18},{"id":"2008.01217","title":"Making Coherence Out of Nothing At All: Measuring the Evolution of Gradient Alignment","created":"2020-08-03","cited_by_count":7},{"id":"1807.09659","title":"A Surprising Linear Relationship Predicts Test Performance in Deep Networks","created":"2018-07-25","cited_by_count":4},{"id":"1907.01991","title":"Circuit-Based Intrinsic Methods to Detect Overfitting","created":"2019-07-03","cited_by_count":4},{"id":"2011.03605","title":"Highly Available Data Parallel ML training on Mesh Networks","created":"2020-11-06","cited_by_count":3},{"id":"2011.14066","title":"On Generalization of Adaptive Methods for Over-parameterized Linear Regression","created":"2020-11-28","cited_by_count":3}],"next_cursor":null}