{"list":"other","total":57,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1606.04934","title":"Improving Variational Inference with Inverse Autoregressive Flow","created":"2016-06-15","cited_by_count":640},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"2002.08791","title":"Bayesian Deep Learning and a Probabilistic Perspective of Generalization","created":"2020-02-20","cited_by_count":480},{"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":"1502.05336","title":"Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks","created":"2015-02-18","cited_by_count":295},{"id":"1706.04454","title":"Empirical Analysis of the Hessian of Over-Parametrized Neural Networks","created":"2017-06-14","cited_by_count":290},{"id":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"id":"1705.08292","title":"The Marginal Value of Adaptive Gradient Methods in Machine Learning","created":"2017-05-23","cited_by_count":250},{"id":"2005.07186","title":"Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors","created":"2020-05-14","cited_by_count":171},{"id":"1506.02158","title":"Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference","created":"2015-06-06","cited_by_count":159},{"id":"1906.02506","title":"Practical Deep Learning with Bayesian Principles","created":"2019-06-06","cited_by_count":158},{"id":"1703.01961","title":"Multiplicative Normalizing Flows for Variational Bayesian Neural Networks","created":"2017-03-06","cited_by_count":157},{"id":"1806.04854","title":"Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam","created":"2018-06-13","cited_by_count":131},{"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":"1712.07628","title":"Improving Generalization Performance by Switching from Adam to SGD","created":"2017-12-20","cited_by_count":125},{"id":"1705.08665","title":"Bayesian Compression for Deep Learning","created":"2017-05-24","cited_by_count":116},{"id":"1907.07504","title":"Subspace Inference for Bayesian Deep Learning","created":"2019-07-17","cited_by_count":95},{"id":"1712.02390","title":"Noisy Natural Gradient as Variational Inference","created":"2017-12-06","cited_by_count":94},{"id":"1307.1493","title":"Dropout Training as Adaptive Regularization","created":"2013-07-04","cited_by_count":93},{"id":"1511.02386","title":"Hierarchical Variational Models","created":"2015-11-07","cited_by_count":89},{"id":"1603.04733","title":"Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors","created":"2016-03-15","cited_by_count":82},{"id":"1803.05649","title":"Sylvester Normalizing Flows for Variational Inference","created":"2018-03-15","cited_by_count":72},{"id":"2002.12915","title":"The Implicit and Explicit Regularization Effects of Dropout","created":"2020-02-28","cited_by_count":71},{"id":"1802.06455","title":"Bayesian Uncertainty Estimation for Batch Normalized Deep Networks","created":"2018-02-18","cited_by_count":70},{"id":"1805.11183","title":"Semi-Implicit Variational Inference","created":"2018-05-28","cited_by_count":55},{"id":"1307.2118","title":"A PAC-Bayesian Tutorial with A Dropout Bound","created":"2013-07-08","cited_by_count":43},{"id":"2007.07368","title":"Explicit Regularisation in Gaussian Noise Injections","created":"2020-07-14","cited_by_count":37},{"id":"1803.09327","title":"Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization","created":"2018-03-25","cited_by_count":35},{"id":"1806.05975","title":"Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors","created":"2018-06-13","cited_by_count":35},{"id":"1811.04504","title":"SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient","created":"2018-11-11","cited_by_count":34},{"id":"1906.05323","title":"Specifying Weight Priors in Bayesian Deep Neural Networks with Empirical Bayes","created":"2019-06-12","cited_by_count":32},{"id":"1701.03208","title":"Gaussian variational approximation with a factor covariance structure","created":"2017-01-12","cited_by_count":22},{"id":"1806.09777","title":"On the Implicit Bias of Dropout","created":"2018-06-26","cited_by_count":22},{"id":"1807.01969","title":"Variational Bayesian dropout: pitfalls and fixes","created":"2018-07-05","cited_by_count":22},{"id":"1412.4736","title":"On the Inductive Bias of Dropout","created":"2014-12-15","cited_by_count":19},{"id":"1706.06569","title":"A Unified Approach to Adaptive Regularization in Online and Stochastic Optimization","created":"2017-06-20","cited_by_count":19},{"id":"1810.02789","title":"Doubly Semi-Implicit Variational Inference","created":"2018-10-05","cited_by_count":19},{"id":"2010.12711","title":"On Convergence and Generalization of Dropout Training","created":"2020-10-23","cited_by_count":19},{"id":"1907.04710","title":"Trust-Region Variational Inference with Gaussian Mixture Models","created":"2019-07-10","cited_by_count":14},{"id":"1811.09385","title":"On the Importance of Strong Baselines in Bayesian Deep Learning","created":"2018-11-23","cited_by_count":12},{"id":"1905.11887","title":"On Dropout and Nuclear Norm Regularization","created":"2019-05-28","cited_by_count":12},{"id":"1905.11248","title":"Walsh-Hadamard Variational Inference for Bayesian Deep Learning","created":"2019-05-27","cited_by_count":8},{"id":"1412.7003","title":"A Bayesian encourages dropout","created":"2014-12-22","cited_by_count":6},{"id":"1902.02603","title":"Radial and Directional Posteriors for Bayesian Neural Networks","created":"2019-02-07","cited_by_count":5},{"id":"1907.06288","title":"Learning Neural Networks with Adaptive Regularization","created":"2019-07-14","cited_by_count":5},{"id":"1811.00596","title":"Variational Dropout via Empirical Bayes","created":"2018-11-01","cited_by_count":4},{"id":"1706.02326","title":"Improving Variational Auto-Encoders using convex combination linear Inverse Autoregressive Flow","created":"2017-06-07","cited_by_count":3},{"id":"2009.06111","title":"Machine Learning's Dropout Training is Distributionally Robust Optimal","created":"2020-09-13","cited_by_count":1}],"next_cursor":null}