{"list":"other","total":55,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"1911.08251","title":"General $E(2)$-Equivariant Steerable CNNs","created":"2019-11-19","cited_by_count":446},{"id":"1412.1193","title":"New insights and perspectives on the natural gradient method","created":"2014-12-03","cited_by_count":443},{"id":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"id":"1807.02547","title":"3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data","created":"2018-07-06","cited_by_count":354},{"id":"1807.03247","title":"An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution","created":"2018-07-09","cited_by_count":307},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"1802.03690","title":"On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups","created":"2018-02-11","cited_by_count":300},{"id":"1612.04642","title":"Harmonic Networks: Deep Translation and Rotation Equivariance","created":"2016-12-14","cited_by_count":295},{"id":"1811.02017","title":"A General Theory of Equivariant CNNs on Homogeneous Spaces","created":"2018-11-05","cited_by_count":228},{"id":"2104.09459","title":"A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups","created":"2021-04-19","cited_by_count":187},{"id":"2006.16908","title":"MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning","created":"2020-06-30","cited_by_count":142},{"id":"1602.01407","title":"A Kronecker-factored approximate Fisher matrix for convolution layers","created":"2016-02-03","cited_by_count":141},{"id":"2002.03061","title":"Incorporating Symmetry into Deep Dynamics Models for Improved Generalization","created":"2020-02-08","cited_by_count":126},{"id":"2102.06571","title":"Bayesian Neural Network Priors Revisited","created":"2021-02-12","cited_by_count":121},{"id":"2104.04975","title":"Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning","created":"2021-04-11","cited_by_count":106},{"id":"1909.12057","title":"B-Spline CNNs on Lie Groups","created":"2019-09-26","cited_by_count":97},{"id":"2201.11969","title":"Approximately Equivariant Networks for Imperfectly Symmetric Dynamics","created":"2022-01-28","cited_by_count":97},{"id":"2109.07103","title":"Automatic Symmetry Discovery with Lie Algebra Convolutional Network","created":"2021-09-15","cited_by_count":83},{"id":"1906.06818","title":"Stacked Capsule Autoencoders","created":"2019-06-17","cited_by_count":82},{"id":"2007.02933","title":"Meta-Learning Symmetries by Reparameterization","created":"2020-07-06","cited_by_count":76},{"id":"2112.01388","title":"Residual Pathway Priors for Soft Equivariance Constraints","created":"2021-12-02","cited_by_count":75},{"id":"1905.04919","title":"BayesNAS: A Bayesian Approach for Neural Architecture Search","created":"2019-05-13","cited_by_count":68},{"id":"2006.08437","title":"Depth Uncertainty in Neural Networks","created":"2020-06-15","cited_by_count":57},{"id":"2011.14214","title":"Truly shift-invariant convolutional neural networks","created":"2020-11-28","cited_by_count":53},{"id":"2010.11882","title":"Learning Invariances in Neural Networks","created":"2020-10-22","cited_by_count":52},{"id":"1808.05563","title":"Learning Invariances using the Marginal Likelihood","created":"2018-08-16","cited_by_count":51},{"id":"2007.13657","title":"Towards Learning Convolutions from Scratch","created":"2020-07-27","cited_by_count":46},{"id":"2005.08140","title":"Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes","created":"2020-05-17","cited_by_count":43},{"id":"2202.10638","title":"Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations","created":"2022-02-22","cited_by_count":42},{"id":"2302.00236","title":"Generative Adversarial Symmetry Discovery","created":"2023-02-01","cited_by_count":42},{"id":"1402.4437","title":"Learning the Irreducible Representations of Commutative Lie Groups","created":"2014-02-18","cited_by_count":41},{"id":"2204.07178","title":"Relaxing Equivariance Constraints with Non-stationary Continuous Filters","created":"2022-04-14","cited_by_count":41},{"id":"2208.14960","title":"Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces I: the compact case","created":"2022-08-31","cited_by_count":25},{"id":"2110.13059","title":"Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups","created":"2021-10-25","cited_by_count":22},{"id":"1902.05888","title":"Bayesian Image Classification with Deep Convolutional Gaussian Processes","created":"2019-02-15","cited_by_count":21},{"id":"2106.07512","title":"Last Layer Marginal Likelihood for Invariance Learning","created":"2021-06-14","cited_by_count":21},{"id":"2204.03640","title":"Equivariance Discovery by Learned Parameter-Sharing","created":"2022-04-07","cited_by_count":18},{"id":"1803.10743","title":"Intertwiners between Induced Representations (with Applications to the Theory of Equivariant Neural Networks)","created":"2018-03-28","cited_by_count":16},{"id":"2202.12439","title":"Learning Invariant Weights in Neural Networks","created":"2022-02-25","cited_by_count":16},{"id":"2106.05886","title":"Group Equivariant Subsampling","created":"2021-06-10","cited_by_count":15},{"id":"2306.03968","title":"Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels","created":"2023-06-06","cited_by_count":10},{"id":"2210.05484","title":"Equivariance-aware Architectural Optimization of Neural Networks","created":"2022-10-11","cited_by_count":8},{"id":"2304.14766","title":"Hyperparameter Optimization through Neural Network Partitioning","created":"2023-04-28","cited_by_count":8},{"id":"2302.05400","title":"DNArch: Learning Convolutional Neural Architectures by Backpropagation","created":"2023-02-10","cited_by_count":4}],"next_cursor":null}