{"list":"other","total":170,"rows":[{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"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":"1606.04934","title":"Improving Variational Inference with Inverse Autoregressive Flow","created":"2016-06-15","cited_by_count":640},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"id":"1608.04471","title":"Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm","created":"2016-08-16","cited_by_count":507},{"id":"2002.08791","title":"Bayesian Deep Learning and a Probabilistic Perspective of Generalization","created":"2020-02-20","cited_by_count":480},{"id":"1511.02222","title":"Deep Kernel Learning","created":"2015-11-06","cited_by_count":445},{"id":"1807.01613","title":"Conditional Neural Processes","created":"2018-07-04","cited_by_count":426},{"id":"2006.10108","title":"Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness","created":"2020-06-17","cited_by_count":389},{"id":"1309.6835","title":"Gaussian Processes for Big Data","created":"2013-09-26","cited_by_count":383},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"2007.06823","title":"Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users","created":"2020-07-14","cited_by_count":338},{"id":"1602.02282","title":"Ladder Variational Autoencoders","created":"2016-02-06","cited_by_count":318},{"id":"1804.11271","title":"Gaussian Process Behaviour in Wide Deep Neural Networks","created":"2018-04-30","cited_by_count":317},{"id":"1807.01622","title":"Neural Processes","created":"2018-07-04","cited_by_count":311},{"id":"1502.05336","title":"Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks","created":"2015-02-18","cited_by_count":295},{"id":"1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","created":"2015-02-19","cited_by_count":284},{"id":"1901.05761","title":"Attentive Neural Processes","created":"2019-01-17","cited_by_count":283},{"id":"1806.02817","title":"Probabilistic Model-Agnostic Meta-Learning","created":"2018-06-07","cited_by_count":256},{"id":"1705.07120","title":"VAE with a VampPrior","created":"2017-05-19","cited_by_count":248},{"id":"2002.10118","title":"Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks","created":"2020-02-24","cited_by_count":231},{"id":"1611.02648","title":"Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders","created":"2016-11-08","cited_by_count":220},{"id":"1611.05148","title":"Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering","created":"2016-11-16","cited_by_count":220},{"id":"1806.03335","title":"Randomized Prior Functions for Deep Reinforcement Learning","created":"2018-06-08","cited_by_count":219},{"id":"1902.03932","title":"Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning","created":"2019-02-11","cited_by_count":203},{"id":"1806.03836","title":"Bayesian Model-Agnostic Meta-Learning","created":"2018-06-11","cited_by_count":194},{"id":"2011.14522","title":"Feature Learning in Infinite-Width Neural Networks","created":"2020-11-30","cited_by_count":190},{"id":"1804.00891","title":"Hyperspherical Variational Auto-Encoders","created":"2018-04-03","cited_by_count":189},{"id":"1801.08930","title":"Recasting Gradient-Based Meta-Learning as Hierarchical Bayes","created":"2018-01-26","cited_by_count":180},{"id":"1611.02731","title":"Variational Lossy Autoencoder","created":"2016-11-08","cited_by_count":176},{"id":"1907.04155","title":"GP-VAE: Deep Probabilistic Time Series Imputation","created":"2019-07-09","cited_by_count":172},{"id":"2005.07186","title":"Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors","created":"2020-05-14","cited_by_count":171},{"id":"1810.05148","title":"Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes","created":"2018-10-11","cited_by_count":167},{"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":"1703.07608","title":"Deep Exploration via Randomized Value Functions","created":"2017-03-22","cited_by_count":156},{"id":"1704.07520","title":"Stein Variational Gradient Descent as Gradient Flow","created":"2017-04-25","cited_by_count":152},{"id":"1910.12478","title":"Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes","created":"2019-10-28","cited_by_count":151},{"id":"2006.13570","title":"Hyperparameter Ensembles for Robustness and Uncertainty Quantification","created":"2020-06-24","cited_by_count":150},{"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":"1705.08933","title":"Doubly Stochastic Variational Inference for Deep Gaussian Processes","created":"2017-05-24","cited_by_count":143},{"id":"2006.14548","title":"Tensor Programs II: Neural Tangent Kernel for Any Architecture","created":"2020-06-25","cited_by_count":143},{"id":"1910.13556","title":"Convolutional Conditional Neural Processes","created":"2019-10-29","cited_by_count":142},{"id":"2007.08792","title":"Uncertainty Quantification and Deep Ensembles","created":"2020-07-17","cited_by_count":139},{"id":"1808.05587","title":"Deep Convolutional Networks as shallow Gaussian Processes","created":"2018-08-16","cited_by_count":138},{"id":"1302.4245","title":"Gaussian Process Kernels for Pattern Discovery and Extrapolation","created":"2013-02-18","cited_by_count":132},{"id":"1903.05779","title":"Functional Variational Bayesian Neural Networks","created":"2019-03-14","cited_by_count":127},{"id":"1906.00722","title":"Topological Autoencoders","created":"2019-06-03","cited_by_count":127},{"id":"2102.06571","title":"Bayesian Neural Network Priors Revisited","created":"2021-02-12","cited_by_count":121},{"id":"1705.08665","title":"Bayesian Compression for Deep Learning","created":"2017-05-24","cited_by_count":116},{"id":"1909.05989","title":"Finite Depth and Width Corrections to the Neural Tangent Kernel","created":"2019-09-13","cited_by_count":115},{"id":"2104.04975","title":"Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning","created":"2021-04-11","cited_by_count":106},{"id":"2006.08205","title":"Learning Latent Space Energy-Based Prior Model","created":"2020-06-15","cited_by_count":104},{"id":"1412.3730","title":"Inconsistency of Bayesian Inference for Misspecified Linear Models, and a Proposal for Repairing It","created":"2014-12-11","cited_by_count":95},{"id":"1712.02390","title":"Noisy Natural Gradient as Variational Inference","created":"2017-12-06","cited_by_count":94},{"id":"1611.00336","title":"Stochastic Variational Deep Kernel Learning","created":"2016-11-01","cited_by_count":93},{"id":"1912.03820","title":"Meta-Learning without Memorization","created":"2019-12-09","cited_by_count":92},{"id":"2007.05864","title":"Bayesian Deep Ensembles via the Neural Tangent Kernel","created":"2020-07-11","cited_by_count":90},{"id":"1906.01930","title":"Approximate Inference Turns Deep Networks into Gaussian Processes","created":"2019-06-05","cited_by_count":89},{"id":"1302.4922","title":"Structure Discovery in Nonparametric Regression through Compositional Kernel Search","created":"2013-02-20","cited_by_count":88},{"id":"1809.11142","title":"EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE","created":"2018-09-28","cited_by_count":87},{"id":"1910.01663","title":"Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks","created":"2019-10-03","cited_by_count":87},{"id":"2002.05551","title":"PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees","created":"2020-02-13","cited_by_count":85},{"id":"1603.04733","title":"Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors","created":"2016-03-15","cited_by_count":82},{"id":"2102.12108","title":"The Promises and Pitfalls of Deep Kernel Learning","created":"2021-02-24","cited_by_count":81},{"id":"1402.5876","title":"Manifold Gaussian Processes for Regression","created":"2014-02-24","cited_by_count":80},{"id":"1905.12200","title":"A Topology Layer for Machine Learning","created":"2019-05-29","cited_by_count":80},{"id":"2007.01332","title":"Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes","created":"2020-07-02","cited_by_count":76},{"id":"1810.11738","title":"Gaussian Process Prior Variational Autoencoders","created":"2018-10-28","cited_by_count":72},{"id":"1611.05013","title":"PixelVAE: A Latent Variable Model for Natural Images","created":"2016-11-15","cited_by_count":70},{"id":"1906.04724","title":"Large Scale Structure of Neural Network Loss Landscapes","created":"2019-06-11","cited_by_count":68},{"id":"1710.04759","title":"Bayesian Hypernetworks","created":"2017-10-13","cited_by_count":66},{"id":"1907.02911","title":"Weight-space symmetry in deep networks gives rise to permutation saddles, connected by equal-loss valleys across the loss landscape","created":"2019-07-05","cited_by_count":63},{"id":"2006.13057","title":"PAC-Bayes Analysis Beyond the Usual Bounds","created":"2020-06-23","cited_by_count":63},{"id":"2006.09797","title":"A Non-Asymptotic Analysis for Stein Variational Gradient Descent","created":"2020-06-17","cited_by_count":61},{"id":"2011.12829","title":"All You Need is a Good Functional Prior for Bayesian Deep Learning","created":"2020-11-25","cited_by_count":61},{"id":"1806.02199","title":"SOM-VAE: Interpretable Discrete Representation Learning on Time Series","created":"2018-06-06","cited_by_count":60},{"id":"1906.09686","title":"Quality of Uncertainty Quantification for Bayesian Neural Network Inference","created":"2019-06-24","cited_by_count":59},{"id":"1810.11428","title":"Resampled Priors for Variational Autoencoders","created":"2018-10-26","cited_by_count":57},{"id":"1812.03973","title":"Bayesian Layers: A Module for Neural Network Uncertainty","created":"2018-12-10","cited_by_count":57},{"id":"1808.05563","title":"Learning Invariances using the Marginal Likelihood","created":"2018-08-16","cited_by_count":51},{"id":"2009.10685","title":"Tensor Programs III: Neural Matrix Laws","created":"2020-09-22","cited_by_count":49},{"id":"1707.02476","title":"Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks","created":"2017-07-08","cited_by_count":48},{"id":"1402.4306","title":"Student-t Processes as Alternatives to Gaussian Processes","created":"2014-02-18","cited_by_count":45},{"id":"1605.06197","title":"Stick-Breaking Variational Autoencoders","created":"2016-05-20","cited_by_count":44},{"id":"1709.01894","title":"Convolutional Gaussian Processes","created":"2017-09-06","cited_by_count":44},{"id":"1906.08324","title":"The Functional Neural Process","created":"2019-06-19","cited_by_count":43},{"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}],"next_cursor":"100"}