{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"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":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"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":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"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":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"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":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1906.02845","title":"Likelihood Ratios for Out-of-Distribution Detection","created":"2019-06-07","cited_by_count":453},{"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":"1412.6614","title":"In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning","created":"2014-12-20","cited_by_count":342},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"1502.05336","title":"Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks","created":"2015-02-18","cited_by_count":295},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293},{"id":"1901.10159","title":"An Investigation into Neural Net Optimization via Hessian Eigenvalue Density","created":"2019-01-29","cited_by_count":292},{"id":"2002.10118","title":"Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks","created":"2020-02-24","cited_by_count":231},{"id":"2007.15801","title":"Finite Versus Infinite Neural Networks: an Empirical Study","created":"2020-07-31","cited_by_count":157},{"id":"2006.07322","title":"Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks","created":"2020-06-12","cited_by_count":138},{"id":"1804.05862","title":"Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach","created":"2018-04-16","cited_by_count":126},{"id":"1706.05350","title":"L2 Regularization versus Batch and Weight Normalization","created":"2017-06-16","cited_by_count":124},{"id":"1506.02617","title":"Path-SGD: Path-Normalized Optimization in Deep Neural Networks","created":"2015-06-08","cited_by_count":120},{"id":"1810.12281","title":"Three Mechanisms of Weight Decay Regularization","created":"2018-10-29","cited_by_count":113},{"id":"2007.12911","title":"Tighter risk certificates for neural networks","created":"2020-07-25","cited_by_count":112},{"id":"1711.01530","title":"Fisher-Rao Metric, Geometry, and Complexity of Neural Networks","created":"2017-11-05","cited_by_count":100},{"id":"1906.06307","title":"A Signal Propagation Perspective for Pruning Neural Networks at Initialization","created":"2019-06-14","cited_by_count":96},{"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":"2001.00939","title":"Relative Flatness and Generalization","created":"2020-01-03","cited_by_count":88},{"id":"2010.14689","title":"Bayesian Deep Learning via Subnetwork Inference","created":"2020-10-28","cited_by_count":87},{"id":"1906.11537","title":"'In-Between' Uncertainty in Bayesian Neural Networks","created":"2019-06-27","cited_by_count":80},{"id":"1802.06455","title":"Bayesian Uncertainty Estimation for Batch Normalized Deep Networks","created":"2018-02-18","cited_by_count":70},{"id":"2010.09649","title":"Hutch++: Optimal Stochastic Trace Estimation","created":"2020-10-19","cited_by_count":63},{"id":"2012.14193","title":"Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization","created":"2020-12-28","cited_by_count":62},{"id":"1901.04653","title":"Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks using PAC-Bayesian Analysis","created":"2019-01-15","cited_by_count":59},{"id":"2103.01439","title":"Fast Adaptation with Linearized Neural Networks","created":"2021-03-02","cited_by_count":32},{"id":"2206.08900","title":"Adapting the Linearised Laplace Model Evidence for Modern Deep Learning","created":"2022-06-17","cited_by_count":29},{"id":"2012.11140","title":"LQF: Linear Quadratic Fine-Tuning","created":"2020-12-21","cited_by_count":25},{"id":"2106.15739","title":"On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay","created":"2021-06-29","cited_by_count":20}],"next_cursor":null}