{"list":"other","total":54,"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":"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":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"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":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"id":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"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":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","created":"2019-12-05","cited_by_count":443},{"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":"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":"2104.14421","title":"What Are Bayesian Neural Network Posteriors Really Like?","created":"2021-04-29","cited_by_count":308},{"id":"1704.04289","title":"Stochastic Gradient Descent as Approximate Bayesian Inference","created":"2017-04-13","cited_by_count":300},{"id":"1906.00695","title":"Continual learning with hypernetworks","created":"2019-06-03","cited_by_count":273},{"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":"1902.03932","title":"Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning","created":"2019-02-11","cited_by_count":203},{"id":"2005.07186","title":"Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors","created":"2020-05-14","cited_by_count":171},{"id":"1905.00076","title":"Ensemble Distribution Distillation","created":"2019-04-30","cited_by_count":158},{"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":"2006.13570","title":"Hyperparameter Ensembles for Robustness and Uncertainty Quantification","created":"2020-06-24","cited_by_count":150},{"id":"1903.05779","title":"Functional Variational Bayesian Neural Networks","created":"2019-03-14","cited_by_count":127},{"id":"2102.06571","title":"Bayesian Neural Network Priors Revisited","created":"2021-02-12","cited_by_count":121},{"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":"2104.04975","title":"Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning","created":"2021-04-11","cited_by_count":106},{"id":"2007.00810","title":"On Linear Identifiability of Learned Representations","created":"2020-07-01","cited_by_count":105},{"id":"2105.06868","title":"Priors in Bayesian Deep Learning: A Review","created":"2021-05-14","cited_by_count":101},{"id":"2007.05864","title":"Bayesian Deep Ensembles via the Neural Tangent Kernel","created":"2020-07-11","cited_by_count":90},{"id":"1901.01608","title":"Scaling description of generalization with number of parameters in deep learning","created":"2019-01-06","cited_by_count":83},{"id":"1912.00894","title":"On the geometry of Stein variational gradient descent","created":"2019-12-02","cited_by_count":82},{"id":"2006.09797","title":"A Non-Asymptotic Analysis for Stein Variational Gradient Descent","created":"2020-06-17","cited_by_count":61},{"id":"1705.07107","title":"Gradient Estimators for Implicit Models","created":"2017-05-19","cited_by_count":58},{"id":"2003.09711","title":"Robust Out-of-distribution Detection for Neural Networks","created":"2020-03-21","cited_by_count":57},{"id":"2101.05544","title":"DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation","created":"2021-01-14","cited_by_count":48},{"id":"1806.02925","title":"A Spectral Approach to Gradient Estimation for Implicit Distributions","created":"2018-06-07","cited_by_count":45},{"id":"2103.01133","title":"Posterior Meta-Replay for Continual Learning","created":"2021-03-01","cited_by_count":45},{"id":"1805.11659","title":"A Unified Particle-Optimization Framework for Scalable Bayesian Sampling","created":"2018-05-29","cited_by_count":44},{"id":"1902.09754","title":"Function Space Particle Optimization for Bayesian Neural Networks","created":"2019-02-26","cited_by_count":41},{"id":"2011.09421","title":"Understanding Variational Inference in Function-Space","created":"2020-11-18","cited_by_count":40},{"id":"2102.01691","title":"Exact Langevin Dynamics with Stochastic Gradients","created":"2021-02-02","cited_by_count":30},{"id":"2007.12927","title":"Neural networks with late-phase weights","created":"2020-07-25","cited_by_count":29},{"id":"2101.09815","title":"Annealed Stein Variational Gradient Descent","created":"2021-01-24","cited_by_count":26},{"id":"2102.06350","title":"Projected Wasserstein gradient descent for high-dimensional Bayesian inference","created":"2021-02-12","cited_by_count":24},{"id":"2106.10760","title":"On Stein Variational Neural Network Ensembles","created":"2021-06-20","cited_by_count":21},{"id":"2105.06964","title":"BNNpriors: A library for Bayesian neural network inference with different prior distributions","created":"2021-05-14","cited_by_count":20},{"id":"2010.14499","title":"A Bayesian Perspective on Training Speed and Model Selection","created":"2020-10-27","cited_by_count":19},{"id":"1511.01754","title":"Symmetry-invariant optimization in deep networks","created":"2015-11-05","cited_by_count":15}],"next_cursor":null}