{"list":"other","total":61,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"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":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1804.06872","title":"Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels","created":"2018-04-18","cited_by_count":1059},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"2002.07394","title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","created":"2020-02-18","cited_by_count":692},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1712.05055","title":"MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels","created":"2017-12-14","cited_by_count":653},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1911.00068","title":"Confident Learning: Estimating Uncertainty in Dataset Labels","created":"2019-10-31","cited_by_count":413},{"id":"2103.14749","title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks","created":"2021-03-26","cited_by_count":395},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"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":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"1412.6544","title":"Qualitatively characterizing neural network optimization problems","created":"2014-12-19","cited_by_count":188},{"id":"2009.08576","title":"Pruning Neural Networks at Initialization: Why are We Missing the Mark?","created":"2020-09-18","cited_by_count":182},{"id":"1806.02612","title":"Dimensionality-Driven Learning with Noisy Labels","created":"2018-06-07","cited_by_count":173},{"id":"1911.05248","title":"What Do Compressed Deep Neural Networks Forget?","created":"2019-11-13","cited_by_count":171},{"id":"1812.05214","title":"Learning to Learn from Noisy Labeled Data","created":"2018-12-13","cited_by_count":160},{"id":"1903.11680","title":"Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks","created":"2019-03-27","cited_by_count":159},{"id":"2002.11328","title":"Rethinking Bias-Variance Trade-off for Generalization of Neural Networks","created":"2020-02-26","cited_by_count":107},{"id":"1906.06307","title":"A Signal Propagation Perspective for Pruning Neural Networks at Initialization","created":"2019-06-14","cited_by_count":96},{"id":"2003.01054","title":"Double Trouble in Double Descent : Bias and Variance(s) in the Lazy Regime","created":"2020-03-02","cited_by_count":95},{"id":"1706.10239","title":"Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes","created":"2017-06-30","cited_by_count":84},{"id":"2106.02890","title":"Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?","created":"2021-06-05","cited_by_count":75},{"id":"2105.14602","title":"On the geometry of generalization and memorization in deep neural networks","created":"2021-05-30","cited_by_count":73},{"id":"1802.07044","title":"The Description Length of Deep Learning Models","created":"2018-02-20","cited_by_count":72},{"id":"1906.10732","title":"The Difficulty of Training Sparse Neural Networks","created":"2019-06-25","cited_by_count":62},{"id":"2103.03014","title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","created":"2021-03-04","cited_by_count":62},{"id":"1906.03728","title":"The Generalization-Stability Tradeoff In Neural Network Pruning","created":"2019-06-09","cited_by_count":54},{"id":"1901.01672","title":"Generalization in Deep Networks: The Role of Distance from Initialization","created":"2019-01-07","cited_by_count":51},{"id":"1903.11257","title":"How Can We Be So Dense? The Benefits of Using Highly Sparse Representations","created":"2019-03-27","cited_by_count":45},{"id":"2004.04328","title":"A Brief Prehistory of Double Descent","created":"2020-04-07","cited_by_count":44},{"id":"2006.15815","title":"Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum","created":"2020-06-29","cited_by_count":40},{"id":"2012.08749","title":"Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks","created":"2020-12-16","cited_by_count":40},{"id":"2002.07933","title":"Improving Generalization by Controlling Label-Noise Information in Neural Network Weights","created":"2020-02-19","cited_by_count":35},{"id":"2011.06220","title":"Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting","created":"2020-11-12","cited_by_count":28},{"id":"2103.17182","title":"Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization","created":"2021-03-31","cited_by_count":28},{"id":"2105.03193","title":"Network Pruning That Matters: A Case Study on Retraining Variants","created":"2021-05-07","cited_by_count":25},{"id":"2103.12002","title":"On the Robustness of Monte Carlo Dropout Trained with Noisy Labels","created":"2021-03-22","cited_by_count":11},{"id":"2009.07439","title":"On the Landscape of One-hidden-layer Sparse Networks and Beyond","created":"2020-09-16","cited_by_count":3}],"next_cursor":null}