{"list":"other","total":77,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"1602.07868","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","created":"2016-02-25","cited_by_count":543},{"id":"1608.04471","title":"Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm","created":"2016-08-16","cited_by_count":507},{"id":"1509.00519","title":"Importance Weighted Autoencoders","created":"2015-09-01","cited_by_count":456},{"id":"1412.1193","title":"New insights and perspectives on the natural gradient method","created":"2014-12-03","cited_by_count":443},{"id":"1512.09300","title":"Autoencoding beyond pixels using a learned similarity metric","created":"2015-12-31","cited_by_count":407},{"id":"1711.01558","title":"Wasserstein Auto-Encoders","created":"2017-11-05","cited_by_count":373},{"id":"1804.03599","title":"Understanding disentangling in $\\beta$-VAE","created":"2018-04-10","cited_by_count":335},{"id":"1401.0118","title":"Black Box Variational Inference","created":"2013-12-31","cited_by_count":319},{"id":"1602.02282","title":"Ladder Variational Autoencoders","created":"2016-02-06","cited_by_count":318},{"id":"1802.05814","title":"Variational Autoencoders for Collaborative Filtering","created":"2018-02-16","cited_by_count":310},{"id":"1906.10652","title":"Monte Carlo Gradient Estimation in Machine Learning","created":"2019-06-25","cited_by_count":283},{"id":"1602.03253","title":"A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluation","created":"2016-02-10","cited_by_count":236},{"id":"1711.05597","title":"Advances in Variational Inference","created":"2017-11-15","cited_by_count":236},{"id":"1611.02731","title":"Variational Lossy Autoencoder","created":"2016-11-08","cited_by_count":176},{"id":"1301.2294","title":"Expectation Propagation for approximate Bayesian inference","created":"2013-01-10","cited_by_count":174},{"id":"2004.04467","title":"Adversarial Latent Autoencoders","created":"2020-04-09","cited_by_count":155},{"id":"1602.02964","title":"A Kernel Test of Goodness of Fit","created":"2016-02-09","cited_by_count":143},{"id":"1801.03558","title":"Inference Suboptimality in Variational Autoencoders","created":"2018-01-10","cited_by_count":132},{"id":"1806.04854","title":"Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam","created":"2018-06-13","cited_by_count":131},{"id":"1903.05779","title":"Functional Variational Bayesian Neural Networks","created":"2019-03-14","cited_by_count":127},{"id":"1602.02311","title":"R\\'enyi Divergence Variational Inference","created":"2016-02-06","cited_by_count":104},{"id":"1807.09356","title":"Iterative Amortized Inference","created":"2018-07-24","cited_by_count":94},{"id":"1401.2753","title":"Stochastic Optimization with Importance Sampling","created":"2014-01-13","cited_by_count":91},{"id":"1511.02386","title":"Hierarchical Variational Models","created":"2015-11-07","cited_by_count":89},{"id":"1901.03416","title":"Preventing Posterior Collapse with delta-VAEs","created":"2019-01-10","cited_by_count":86},{"id":"1802.02550","title":"Semi-Amortized Variational Autoencoders","created":"2018-02-07","cited_by_count":83},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83},{"id":"1702.08139","title":"Improved Variational Autoencoders for Text Modeling using Dilated Convolutions","created":"2017-02-27","cited_by_count":81},{"id":"1301.6725","title":"Loopy Belief Propagation for Approximate Inference: An Empirical Study","created":"2013-01-23","cited_by_count":76},{"id":"1802.04537","title":"Tighter Variational Bounds are Not Necessarily Better","created":"2018-02-13","cited_by_count":76},{"id":"1711.01204","title":"Metrics for Deep Generative Models","created":"2017-11-03","cited_by_count":53},{"id":"2105.14859","title":"Consistency Regularization for Variational Auto-Encoders","created":"2021-05-31","cited_by_count":51},{"id":"1605.06197","title":"Stick-Breaking Variational Autoencoders","created":"2016-05-20","cited_by_count":44},{"id":"1704.02399","title":"Stein Variational Policy Gradient","created":"2017-04-07","cited_by_count":44},{"id":"1511.06406","title":"Denoising Criterion for Variational Auto-Encoding Framework","created":"2015-11-19","cited_by_count":43},{"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":"1602.02283","title":"Importance Sampling for Minibatches","created":"2016-02-06","cited_by_count":36},{"id":"2106.15921","title":"Monte Carlo Variational Auto-Encoders","created":"2021-06-30","cited_by_count":36},{"id":"2006.01524","title":"Neural Control Variates","created":"2020-06-02","cited_by_count":34},{"id":"1702.02390","title":"A Hybrid Convolutional Variational Autoencoder for Text Generation","created":"2017-02-08","cited_by_count":33},{"id":"2002.04881","title":"Learning Flat Latent Manifolds with VAEs","created":"2020-02-12","cited_by_count":33},{"id":"1805.08913","title":"Amortized Inference Regularization","created":"2018-05-23","cited_by_count":30},{"id":"1705.07880","title":"Reducing Reparameterization Gradient Variance","created":"2017-05-22","cited_by_count":27},{"id":"2012.03715","title":"Autoencoding Variational Autoencoder","created":"2020-12-07","cited_by_count":25},{"id":"1807.01604","title":"Quasi-Monte Carlo Variational Inference","created":"2018-07-04","cited_by_count":24},{"id":"1710.06085","title":"On the challenges of learning with inference networks on sparse, high-dimensional data","created":"2017-10-17","cited_by_count":21},{"id":"2004.12585","title":"A Batch Normalized Inference Network Keeps the KL Vanishing Away","created":"2020-04-27","cited_by_count":20},{"id":"2003.00605","title":"Stein Variational Inference for Discrete Distributions","created":"2020-03-01","cited_by_count":16},{"id":"2102.08663","title":"Preventing Oversmoothing in VAE via Generalized Variance Parameterization","created":"2021-02-17","cited_by_count":15},{"id":"1901.11033","title":"Metric Gaussian Variational Inference","created":"2019-01-30","cited_by_count":14},{"id":"1411.1670","title":"Stochastic Variational Inference for Hidden Markov Models","created":"2014-11-06","cited_by_count":12},{"id":"2108.13083","title":"An Introduction to Variational Inference","created":"2021-08-30","cited_by_count":12},{"id":"1807.10564","title":"Auto-Encoding Variational Neural Machine Translation","created":"2018-07-27","cited_by_count":11},{"id":"2205.11640","title":"Generalization Gap in Amortized Inference","created":"2022-05-23","cited_by_count":10},{"id":"1509.01631","title":"Stochastic gradient variational Bayes for gamma approximating distributions","created":"2015-09-04","cited_by_count":9},{"id":"1909.13433","title":"Deep Amortized Clustering","created":"2019-09-30","cited_by_count":9},{"id":"1603.01140","title":"Overdispersed Black-Box Variational Inference","created":"2016-03-03","cited_by_count":8},{"id":"1704.05201","title":"Stein Variational Adaptive Importance Sampling","created":"2017-04-18","cited_by_count":8},{"id":"1709.05870","title":"ZhuSuan: A Library for Bayesian Deep Learning","created":"2017-09-18","cited_by_count":8},{"id":"1506.01351","title":"Celeste: Variational inference for a generative model of astronomical images","created":"2015-06-03","cited_by_count":7},{"id":"2102.03151","title":"Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach","created":"2021-02-05","cited_by_count":6},{"id":"1807.05936","title":"Variational Inference: A Unified Framework of Generative Models and Some Revelations","created":"2018-07-16","cited_by_count":3},{"id":"2111.02947","title":"Variational Inference with Holder Bounds","created":"2021-11-04","cited_by_count":3},{"id":"1806.05978","title":"Uncertainty Estimations by Softplus normalization in Bayesian Convolutional Neural Networks with Variational Inference","created":"2018-06-15","cited_by_count":2},{"id":"1506.06100","title":"Approximate Inference with the Variational Holder Bound","created":"2015-06-19","cited_by_count":1}],"next_cursor":null}