{"list":"other","total":59,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"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":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1910.09457","title":"Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods","created":"2019-10-21","cited_by_count":913},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680},{"id":"1603.00943","title":"CVXPY: A Python-Embedded Modeling Language for Convex Optimization","created":"2016-03-03","cited_by_count":641},{"id":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"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":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","created":"2019-12-05","cited_by_count":443},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"1402.4102","title":"Stochastic Gradient Hamiltonian Monte Carlo","created":"2014-02-17","cited_by_count":343},{"id":"1803.00885","title":"Essentially No Barriers in Neural Network Energy Landscape","created":"2018-03-02","cited_by_count":330},{"id":"2104.14421","title":"What Are Bayesian Neural Network Posteriors Really Like?","created":"2021-04-29","cited_by_count":308},{"id":"1502.05336","title":"Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks","created":"2015-02-18","cited_by_count":295},{"id":"2110.06296","title":"The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks","created":"2021-10-12","cited_by_count":291},{"id":"2003.00307","title":"Loss landscapes and optimization in over-parameterized non-linear systems and neural networks","created":"2020-02-29","cited_by_count":233},{"id":"1902.03932","title":"Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning","created":"2019-02-11","cited_by_count":203},{"id":"1709.04494","title":"A Rewriting System for Convex Optimization Problems","created":"2017-09-13","cited_by_count":179},{"id":"2010.06610","title":"Training independent subnetworks for robust prediction","created":"2020-10-13","cited_by_count":177},{"id":"1511.06314","title":"Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks","created":"2015-11-19","cited_by_count":139},{"id":"2006.12024","title":"Bayesian Neural Networks: An Introduction and Survey","created":"2020-06-22","cited_by_count":131},{"id":"1903.05779","title":"Functional Variational Bayesian Neural Networks","created":"2019-03-14","cited_by_count":127},{"id":"1506.02617","title":"Path-SGD: Path-Normalized Optimization in Deep Neural Networks","created":"2015-06-08","cited_by_count":120},{"id":"2106.11642","title":"Repulsive Deep Ensembles are Bayesian","created":"2021-06-22","cited_by_count":104},{"id":"1910.00744","title":"Reverse-Engineering Deep ReLU Networks","created":"2019-10-02","cited_by_count":83},{"id":"2110.15073","title":"MMD Aggregated Two-Sample Test","created":"2021-10-28","cited_by_count":75},{"id":"1906.04724","title":"Large Scale Structure of Neural Network Loss Landscapes","created":"2019-06-11","cited_by_count":68},{"id":"2205.14258","title":"On the Symmetries of Deep Learning Models and their Internal Representations","created":"2022-05-27","cited_by_count":64},{"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":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57},{"id":"1505.02827","title":"On Markov chain Monte Carlo methods for tall data","created":"2015-05-11","cited_by_count":50},{"id":"2210.09184","title":"Packed-Ensembles for Efficient Uncertainty Estimation","created":"2022-10-17","cited_by_count":49},{"id":"2101.05544","title":"DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation","created":"2021-01-14","cited_by_count":48},{"id":"1912.11316","title":"TRADI: Tracking deep neural network weight distributions for uncertainty estimation","created":"2019-12-24","cited_by_count":39},{"id":"2306.06179","title":"Hidden symmetries of ReLU networks","created":"2023-06-09","cited_by_count":39},{"id":"2210.17216","title":"Symmetries, flat minima, and the conserved quantities of gradient flow","created":"2022-10-31","cited_by_count":35},{"id":"1807.02581","title":"The Goldilocks zone: Towards better understanding of neural network loss landscapes","created":"2018-07-06","cited_by_count":32},{"id":"2110.13786","title":"Diversity and Generalization in Neural Network Ensembles","created":"2021-10-26","cited_by_count":32},{"id":"1912.08416","title":"Benchmarking the Neural Linear Model for Regression","created":"2019-12-18","cited_by_count":31},{"id":"2001.08049","title":"On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation","created":"2020-01-22","cited_by_count":23},{"id":"2304.02902","title":"Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetry","created":"2023-04-06","cited_by_count":21},{"id":"2012.02818","title":"Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification","created":"2020-12-04","cited_by_count":18},{"id":"1812.04074","title":"Disciplined Geometric Programming","created":"2018-12-10","cited_by_count":8}],"next_cursor":null}