{"list":"other","total":51,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"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":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"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":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"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":"1912.03263","title":"Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One","created":"2019-12-06","cited_by_count":405},{"id":"1804.11271","title":"Gaussian Process Behaviour in Wide Deep Neural Networks","created":"2018-04-30","cited_by_count":317},{"id":"1710.03667","title":"High-dimensional dynamics of generalization error in neural networks","created":"2017-10-10","cited_by_count":241},{"id":"2003.02218","title":"The large learning rate phase of deep learning: the catapult mechanism","created":"2020-03-04","cited_by_count":216},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"2002.02561","title":"Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks","created":"2020-02-07","cited_by_count":200},{"id":"1611.01232","title":"Deep Information Propagation","created":"2016-11-04","cited_by_count":195},{"id":"1806.05393","title":"Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks","created":"2018-06-14","cited_by_count":176},{"id":"1810.05148","title":"Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes","created":"2018-10-11","cited_by_count":167},{"id":"2006.13198","title":"Spectral Bias and Task-Model Alignment Explain Generalization in Kernel Regression and Infinitely Wide Neural Networks","created":"2020-06-23","cited_by_count":166},{"id":"2007.15801","title":"Finite Versus Infinite Neural Networks: an Empirical Study","created":"2020-07-31","cited_by_count":157},{"id":"1902.04760","title":"Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation","created":"2019-02-13","cited_by_count":149},{"id":"1912.02803","title":"Neural Tangents: Fast and Easy Infinite Neural Networks in Python","created":"2019-12-05","cited_by_count":149},{"id":"1808.05587","title":"Deep Convolutional Networks as shallow Gaussian Processes","created":"2018-08-16","cited_by_count":138},{"id":"2002.09339","title":"Generalisation error in learning with random features and the hidden manifold model","created":"2020-02-21","cited_by_count":127},{"id":"1909.05989","title":"Finite Depth and Width Corrections to the Neural Tangent Kernel","created":"2019-09-13","cited_by_count":115},{"id":"1702.07254","title":"Sobolev Norm Learning Rates for Regularized Least-Squares Algorithm","created":"2017-02-23","cited_by_count":114},{"id":"2008.06786","title":"The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization","created":"2020-08-15","cited_by_count":101},{"id":"2003.01054","title":"Double Trouble in Double Descent : Bias and Variance(s) in the Lazy Regime","created":"2020-03-02","cited_by_count":95},{"id":"2102.04074","title":"Learning Curve Theory","created":"2021-02-08","cited_by_count":85},{"id":"1901.01608","title":"Scaling description of generalization with number of parameters in deep learning","created":"2019-01-06","cited_by_count":83},{"id":"1910.00019","title":"Non-Gaussian processes and neural networks at finite widths","created":"2019-09-30","cited_by_count":78},{"id":"1909.11304","title":"Asymptotics of Wide Networks from Feynman Diagrams","created":"2019-09-25","cited_by_count":77},{"id":"2011.03321","title":"Understanding Double Descent Requires a Fine-Grained Bias-Variance Decomposition","created":"2020-11-04","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":"2003.02237","title":"Neural Kernels Without Tangents","created":"2020-03-04","cited_by_count":56},{"id":"2004.10802","title":"A Neural Scaling Law from the Dimension of the Data Manifold","created":"2020-04-22","cited_by_count":52},{"id":"2009.08092","title":"Distributional Generalization: A New Kind of Generalization","created":"2020-09-17","cited_by_count":42},{"id":"1912.07242","title":"More Data Can Hurt for Linear Regression: Sample-wise Double Descent","created":"2019-12-16","cited_by_count":37},{"id":"2006.10621","title":"On the Predictability of Pruning Across Scales","created":"2020-06-18","cited_by_count":33},{"id":"2008.08675","title":"Asymptotics of Wide Convolutional Neural Networks","created":"2020-08-19","cited_by_count":16},{"id":"1906.05301","title":"Learning Curves for Deep Neural Networks: A Gaussian Field Theory Perspective","created":"2019-06-12","cited_by_count":11},{"id":"2011.12547","title":"Implicit bias of deep linear networks in the large learning rate phase","created":"2020-11-25","cited_by_count":3}],"next_cursor":null}