{"list":"other","total":52,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"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":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"1308.0850","title":"Generating Sequences With Recurrent Neural Networks","created":"2013-08-04","cited_by_count":554},{"id":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"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":"1412.1193","title":"New insights and perspectives on the natural gradient method","created":"2014-12-03","cited_by_count":443},{"id":"1309.6835","title":"Gaussian Processes for Big Data","created":"2013-09-26","cited_by_count":383},{"id":"1704.04289","title":"Stochastic Gradient Descent as Approximate Bayesian Inference","created":"2017-04-13","cited_by_count":300},{"id":"1502.05336","title":"Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks","created":"2015-02-18","cited_by_count":295},{"id":"1705.08292","title":"The Marginal Value of Adaptive Gradient Methods in Machine Learning","created":"2017-05-23","cited_by_count":250},{"id":"1711.05597","title":"Advances in Variational Inference","created":"2017-11-15","cited_by_count":236},{"id":"1903.05662","title":"Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets","created":"2019-03-13","cited_by_count":231},{"id":"1705.07832","title":"Concrete Dropout","created":"2017-05-22","cited_by_count":227},{"id":"1306.6430","title":"A General Framework for Updating Belief Distributions","created":"2013-06-27","cited_by_count":175},{"id":"1301.3584","title":"Revisiting Natural Gradient for Deep Networks","created":"2013-01-16","cited_by_count":159},{"id":"1906.02506","title":"Practical Deep Learning with Bayesian Principles","created":"2019-06-06","cited_by_count":158},{"id":"1806.04854","title":"Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam","created":"2018-06-13","cited_by_count":131},{"id":"1710.11029","title":"Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks","created":"2017-10-30","cited_by_count":109},{"id":"1712.02390","title":"Noisy Natural Gradient as Variational Inference","created":"2017-12-06","cited_by_count":94},{"id":"1906.01930","title":"Approximate Inference Turns Deep Networks into Gaussian Processes","created":"2019-06-05","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":"1703.04265","title":"Conjugate-Computation Variational Inference : Converting Variational Inference in Non-Conjugate Models to Inferences in Conjugate Models","created":"2017-03-13","cited_by_count":65},{"id":"1809.10756","title":"An Introduction to Probabilistic Programming","created":"2018-09-27","cited_by_count":63},{"id":"1301.6677","title":"Relative Loss Bounds for On-line Density Estimation with the Exponential Family of Distributions","created":"2013-01-23","cited_by_count":60},{"id":"1906.02107","title":"Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization","created":"2019-06-05","cited_by_count":60},{"id":"1310.7780","title":"The Information Geometry of Mirror Descent","created":"2013-10-29","cited_by_count":54},{"id":"1906.02914","title":"Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations","created":"2019-06-07","cited_by_count":51},{"id":"1506.04416","title":"Bayesian Dark Knowledge","created":"2015-06-14","cited_by_count":45},{"id":"1803.09151","title":"Natural Gradients in Practice: Non-Conjugate Variational Inference in Gaussian Process Models","created":"2018-03-24","cited_by_count":38},{"id":"1807.04489","title":"Fast yet Simple Natural-Gradient Descent for Variational Inference in Complex Models","created":"2018-07-12","cited_by_count":38},{"id":"1503.03712","title":"On Graduated Optimization for Stochastic Non-Convex Problems","created":"2015-03-12","cited_by_count":34},{"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":"1802.07543","title":"The Many Faces of Exponential Weights in Online Learning","created":"2018-02-21","cited_by_count":33},{"id":"1703.00209","title":"Online Natural Gradient as a Kalman Filter","created":"2017-03-01","cited_by_count":25},{"id":"2002.10778","title":"Training Binary Neural Networks using the Bayesian Learning Rule","created":"2020-02-25","cited_by_count":23},{"id":"2102.07405","title":"Tractable structured natural gradient descent using local parameterizations","created":"2021-02-15","cited_by_count":22},{"id":"2007.04731","title":"Fast Variational Learning in State-Space Gaussian Process Models","created":"2020-07-09","cited_by_count":20},{"id":"1910.13398","title":"Stein's Lemma for the Reparameterization Trick with Exponential Family Mixtures","created":"2019-10-29","cited_by_count":18},{"id":"2011.01170","title":"Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent","created":"2020-11-02","cited_by_count":18},{"id":"1604.00860","title":"Bayesian Computing with INLA: A Review","created":"2016-04-04","cited_by_count":16},{"id":"1807.07540","title":"Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods","created":"2018-07-19","cited_by_count":9},{"id":"1508.00457","title":"Evolutionary Multimodal Optimization: A Short Survey","created":"2015-08-03","cited_by_count":5},{"id":"1612.03957","title":"Monte Carlo Structured SVI for Two-Level Non-Conjugate Models","created":"2016-12-12","cited_by_count":3},{"id":"1902.04107","title":"Divergence-Based Motivation for Online EM and Combining Hidden Variable Models","created":"2019-02-11","cited_by_count":1}],"next_cursor":null}