{"list":"other","total":87,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"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":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1708.05031","title":"Neural Collaborative Filtering","created":"2017-08-16","cited_by_count":1111},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"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":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"id":"1712.01887","title":"Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training","created":"2017-12-05","cited_by_count":478},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1412.1193","title":"New insights and perspectives on the natural gradient method","created":"2014-12-03","cited_by_count":443},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1711.00489","title":"Don't Decay the Learning Rate, Increase the Batch Size","created":"2017-11-01","cited_by_count":320},{"id":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"id":"1705.08741","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","created":"2017-05-24","cited_by_count":279},{"id":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"1404.5997","title":"One weird trick for parallelizing convolutional neural networks","created":"2014-04-23","cited_by_count":264},{"id":"1705.07878","title":"TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning","created":"2017-05-22","cited_by_count":256},{"id":"1705.08292","title":"The Marginal Value of Adaptive Gradient Methods in Machine Learning","created":"2017-05-23","cited_by_count":250},{"id":"1704.05021","title":"Sparse Communication for Distributed Gradient Descent","created":"2017-04-17","cited_by_count":249},{"id":"1503.02101","title":"Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition","created":"2015-03-06","cited_by_count":243},{"id":"1809.10505","title":"The Convergence of Sparsified Gradient Methods","created":"2018-09-27","cited_by_count":229},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"1710.09854","title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","created":"2017-10-26","cited_by_count":201},{"id":"1811.03600","title":"Measuring the Effects of Data Parallelism on Neural Network Training","created":"2018-11-08","cited_by_count":193},{"id":"1802.09941","title":"Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis","created":"2018-02-26","cited_by_count":156},{"id":"1610.02132","title":"QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding","created":"2016-10-07","cited_by_count":147},{"id":"1706.03662","title":"Practical Gauss-Newton Optimisation for Deep Learning","created":"2017-06-12","cited_by_count":142},{"id":"1602.01407","title":"A Kronecker-factored approximate Fisher matrix for convolution layers","created":"2016-02-03","cited_by_count":141},{"id":"1907.04164","title":"Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model","created":"2019-07-09","cited_by_count":117},{"id":"1910.05446","title":"On Empirical Comparisons of Optimizers for Deep Learning","created":"2019-10-11","cited_by_count":103},{"id":"1804.07612","title":"Revisiting Small Batch Training for Deep Neural Networks","created":"2018-04-20","cited_by_count":102},{"id":"1708.01012","title":"On the convergence properties of a $K$-step averaging stochastic gradient descent algorithm for nonconvex optimization","created":"2017-08-03","cited_by_count":92},{"id":"1905.10988","title":"Natural Compression for Distributed Deep Learning","created":"2019-05-27","cited_by_count":90},{"id":"2006.15081","title":"On the Generalization Benefit of Noise in Stochastic Gradient Descent","created":"2020-06-26","cited_by_count":82},{"id":"2102.02888","title":"1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed","created":"2021-02-04","cited_by_count":75},{"id":"1912.08957","title":"Optimization for deep learning: theory and algorithms","created":"2019-12-19","cited_by_count":70},{"id":"2006.08877","title":"Practical Quasi-Newton Methods for Training Deep Neural Networks","created":"2020-06-16","cited_by_count":68},{"id":"1807.11205","title":"Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes","created":"2018-07-30","cited_by_count":63},{"id":"2107.11817","title":"Go Wider Instead of Deeper","created":"2021-07-25","cited_by_count":57},{"id":"1609.08502","title":"Exact and Inexact Subsampled Newton Methods for Optimization","created":"2016-09-27","cited_by_count":38},{"id":"1811.12019","title":"Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks","created":"2018-11-29","cited_by_count":37},{"id":"1903.05499","title":"DeepOBS: A Deep Learning Optimizer Benchmark Suite","created":"2019-03-13","cited_by_count":37},{"id":"1708.07827","title":"Second-Order Optimization for Non-Convex Machine Learning: An Empirical Study","created":"2017-08-25","cited_by_count":35},{"id":"2008.03911","title":"A Survey on Large-scale Machine Learning","created":"2020-08-10","cited_by_count":35},{"id":"1712.02679","title":"AdaComp : Adaptive Residual Gradient Compression for Data-Parallel Distributed Training","created":"2017-12-07","cited_by_count":33},{"id":"1606.07365","title":"Parallel SGD: When does averaging help?","created":"2016-06-23","cited_by_count":32},{"id":"1807.03210","title":"Efficient Decentralized Deep Learning by Dynamic Model Averaging","created":"2018-07-09","cited_by_count":30},{"id":"1712.02029","title":"AdaBatch: Adaptive Batch Sizes for Training Deep Neural Networks","created":"2017-12-06","cited_by_count":29},{"id":"2104.06069","title":"1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed","created":"2021-04-13","cited_by_count":24},{"id":"2007.00784","title":"Convolutional Neural Network Training with Distributed K-FAC","created":"2020-07-01","cited_by_count":22},{"id":"1611.00756","title":"Accelerated Methods for Non-Convex Optimization","created":"2016-11-02","cited_by_count":20},{"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":"1901.11150","title":"Memory-Efficient Adaptive Optimization","created":"2019-01-30","cited_by_count":19},{"id":"1908.06077","title":"NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization","created":"2019-08-16","cited_by_count":18},{"id":"1811.06992","title":"Image Classification at Supercomputer Scale","created":"2018-11-16","cited_by_count":16},{"id":"1602.03943","title":"Second-Order Stochastic Optimization for Machine Learning in Linear Time","created":"2016-02-12","cited_by_count":14},{"id":"1903.12650","title":"Yet Another Accelerated SGD: ResNet-50 Training on ImageNet in 74.7 seconds","created":"2019-03-29","cited_by_count":12},{"id":"1611.01146","title":"Finding Approximate Local Minima Faster than Gradient Descent","created":"2016-11-03","cited_by_count":8}],"next_cursor":null}