{"list":"other","total":68,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"id":"1904.03751","title":"DeepGCNs: Can GCNs Go as Deep as CNNs?","created":"2019-04-07","cited_by_count":527},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396},{"id":"1604.06778","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","created":"2016-04-22","cited_by_count":371},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"1912.02365","title":"Lower Bounds for Non-Convex Stochastic Optimization","created":"2019-12-05","cited_by_count":307},{"id":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297},{"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":"2010.07468","title":"AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients","created":"2020-10-15","cited_by_count":283},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260},{"id":"2006.07739","title":"DeeperGCN: All You Need to Train Deeper GCNs","created":"2020-06-13","cited_by_count":250},{"id":"1902.09843","title":"Adaptive Gradient Methods with Dynamic Bound of Learning Rate","created":"2019-02-26","cited_by_count":183},{"id":"1806.00900","title":"Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced","created":"2018-06-04","cited_by_count":177},{"id":"1906.04908","title":"SPoC: Search-based Pseudocode to Code","created":"2019-06-12","cited_by_count":176},{"id":"1808.02941","title":"On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization","created":"2018-08-08","cited_by_count":174},{"id":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143},{"id":"2002.03305","title":"Momentum Improves Normalized SGD","created":"2020-02-09","cited_by_count":139},{"id":"1705.09886","title":"Convergence Analysis of Two-layer Neural Networks with ReLU Activation","created":"2017-05-28","cited_by_count":137},{"id":"2110.03141","title":"Efficient Sharpness-aware Minimization for Improved Training of Neural Networks","created":"2021-10-07","cited_by_count":137},{"id":"2203.02714","title":"Towards Efficient and Scalable Sharpness-Aware Minimization","created":"2022-03-05","cited_by_count":129},{"id":"1611.04231","title":"Identity Matters in Deep Learning","created":"2016-11-14","cited_by_count":109},{"id":"1710.08402","title":"Stability and Generalization of Learning Algorithms that Converge to Global Optima","created":"2017-10-23","cited_by_count":100},{"id":"1808.05671","title":"On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization","created":"2018-08-16","cited_by_count":91},{"id":"1806.06763","title":"Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks","created":"2018-06-18","cited_by_count":90},{"id":"2012.11654","title":"Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks","created":"2020-12-21","cited_by_count":87},{"id":"1711.10456","title":"Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent","created":"2017-11-28","cited_by_count":66},{"id":"2002.07867","title":"Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology","created":"2020-02-18","cited_by_count":66},{"id":"2203.14415","title":"Mugs: A Multi-Granular Self-Supervised Learning Framework","created":"2022-03-27","cited_by_count":54},{"id":"2112.03459","title":"A Novel Convergence Analysis for Algorithms of the Adam Family","created":"2021-12-07","cited_by_count":50},{"id":"2202.00089","title":"Understanding AdamW through Proximal Methods and Scale-Freeness","created":"2022-01-31","cited_by_count":46},{"id":"1902.00247","title":"Sharp Analysis for Nonconvex SGD Escaping from Saddle Points","created":"2019-02-01","cited_by_count":40},{"id":"2006.13476","title":"Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations","created":"2020-06-24","cited_by_count":40},{"id":"2006.15815","title":"Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum","created":"2020-06-29","cited_by_count":40},{"id":"1611.03131","title":"Diverse Neural Network Learns True Target Functions","created":"2016-11-09","cited_by_count":33},{"id":"2102.06356","title":"A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes","created":"2021-02-12","cited_by_count":20},{"id":"2011.11985","title":"Adam$^+$: A Stochastic Method with Adaptive Variance Reduction","created":"2020-11-24","cited_by_count":18},{"id":"2201.11411","title":"Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the $O(\\epsilon^{-7/4})$ Complexity","created":"2022-01-27","cited_by_count":17},{"id":"1309.1501","title":"Improvements to deep convolutional neural networks for LVCSR","created":"2013-09-05","cited_by_count":11},{"id":"2111.00856","title":"Large-Scale Deep Learning Optimizations: A Comprehensive Survey","created":"2021-11-01","cited_by_count":10},{"id":"1710.06910","title":"Characterization of Gradient Dominance and Regularity Conditions for Neural Networks","created":"2017-10-18","cited_by_count":8}],"next_cursor":null}