{"list":"other","total":55,"rows":[{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"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":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"id":"1610.02415","title":"Automatic chemical design using a data-driven continuous representation of molecules","created":"2016-10-07","cited_by_count":765},{"id":"1802.04364","title":"Junction Tree Variational Autoencoder for Molecular Graph Generation","created":"2018-02-12","cited_by_count":652},{"id":"1809.11165","title":"GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration","created":"2018-09-28","cited_by_count":609},{"id":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"id":"1906.12340","title":"Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty","created":"2019-06-28","cited_by_count":514},{"id":"1406.5298","title":"Semi-Supervised Learning with Deep Generative Models","created":"2014-06-20","cited_by_count":496},{"id":"1511.02222","title":"Deep Kernel Learning","created":"2015-11-06","cited_by_count":445},{"id":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","created":"2019-12-05","cited_by_count":443},{"id":"1807.00263","title":"Accurate Uncertainties for Deep Learning Using Calibrated Regression","created":"2018-07-01","cited_by_count":422},{"id":"1910.01739","title":"Scalable Global Optimization via Local Bayesian Optimization","created":"2019-10-03","cited_by_count":374},{"id":"1711.10561","title":"Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations","created":"2017-11-28","cited_by_count":373},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"1704.00109","title":"Snapshot Ensembles: Train 1, get M for free","created":"2017-04-01","cited_by_count":350},{"id":"2006.11287","title":"Discovering Symbolic Models from Deep Learning with Inductive Biases","created":"2020-06-19","cited_by_count":344},{"id":"1704.02901","title":"Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs","created":"2017-04-10","cited_by_count":310},{"id":"1703.01925","title":"Grammar Variational Autoencoder","created":"2017-03-06","cited_by_count":285},{"id":"1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","created":"2015-02-19","cited_by_count":284},{"id":"1807.01065","title":"When Gaussian Process Meets Big Data: A Review of Scalable GPs","created":"2018-07-03","cited_by_count":206},{"id":"1902.03932","title":"Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning","created":"2019-02-11","cited_by_count":203},{"id":"1906.01620","title":"Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision","created":"2019-06-04","cited_by_count":182},{"id":"2010.06610","title":"Training independent subnetworks for robust prediction","created":"2020-10-13","cited_by_count":177},{"id":"1802.09127","title":"Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling","created":"2018-02-26","cited_by_count":169},{"id":"1703.01961","title":"Multiplicative Normalizing Flows for Variational Bayesian Neural Networks","created":"2017-03-06","cited_by_count":157},{"id":"1912.02803","title":"Neural Tangents: Fast and Easy Infinite Neural Networks in Python","created":"2019-12-05","cited_by_count":149},{"id":"2104.10201","title":"Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020","created":"2021-04-20","cited_by_count":148},{"id":"1809.08327","title":"Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems","created":"2018-09-21","cited_by_count":147},{"id":"1605.07079","title":"Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets","created":"2016-05-23","cited_by_count":132},{"id":"1710.11431","title":"Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling","created":"2017-10-31","cited_by_count":131},{"id":"1903.05779","title":"Functional Variational Bayesian Neural Networks","created":"2019-03-14","cited_by_count":127},{"id":"2006.09191","title":"Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining","created":"2020-06-16","cited_by_count":123},{"id":"1903.08114","title":"Exact Gaussian Processes on a Million Data Points","created":"2019-03-19","cited_by_count":119},{"id":"1706.01445","title":"Batched Large-scale Bayesian Optimization in High-dimensional Spaces","created":"2017-06-05","cited_by_count":117},{"id":"1805.10196","title":"Maximizing acquisition functions for Bayesian optimization","created":"2018-05-25","cited_by_count":114},{"id":"2012.10885","title":"LieTransformer: Equivariant self-attention for Lie Groups","created":"2020-12-20","cited_by_count":100},{"id":"1406.3896","title":"Freeze-Thaw Bayesian Optimization","created":"2014-06-16","cited_by_count":90},{"id":"1808.05697","title":"Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study","created":"2018-08-16","cited_by_count":90},{"id":"2007.00708","title":"Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search","created":"2020-07-01","cited_by_count":89},{"id":"1908.01425","title":"ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendations","created":"2019-08-05","cited_by_count":77},{"id":"1904.08875","title":"DScribe: Library of Descriptors for Machine Learning in Materials Science","created":"2019-04-18","cited_by_count":63},{"id":"2006.12138","title":"Graph Neural Networks in TensorFlow and Keras with Spektral","created":"2020-06-22","cited_by_count":60},{"id":"1906.01537","title":"Bayesian Optimization of Composite Functions","created":"2019-06-04","cited_by_count":46},{"id":"1709.01894","title":"Convolutional Gaussian Processes","created":"2017-09-06","cited_by_count":44},{"id":"1703.02628","title":"Global optimization of Lipschitz functions","created":"2017-03-07","cited_by_count":39},{"id":"1911.06287","title":"Scalable Exact Inference in Multi-Output Gaussian Processes","created":"2019-11-14","cited_by_count":25},{"id":"1907.06011","title":"Extracting Interpretable Physical Parameters from Spatiotemporal Systems using Unsupervised Learning","created":"2019-07-13","cited_by_count":23},{"id":"1905.05739","title":"Graph Convolutional Gaussian Processes","created":"2019-05-14","cited_by_count":20},{"id":"2010.10969","title":"Incorporating Interpretable Output Constraints in Bayesian Neural Networks","created":"2020-10-21","cited_by_count":10},{"id":"2002.12168","title":"Infinitely Wide Graph Convolutional Networks: Semi-supervised Learning via Gaussian Processes","created":"2020-02-26","cited_by_count":8},{"id":"1405.4350","title":"Robust topology optimization of three-dimensional photonic-crystal band-gap structures","created":"2014-05-17","cited_by_count":2}],"next_cursor":null}