{"list":"other","total":71,"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":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1806.00582","title":"Federated Learning with Non-IID Data","created":"2018-06-02","cited_by_count":1108},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"1909.06335","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","created":"2019-09-13","cited_by_count":851},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"id":"1705.09056","title":"Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent","created":"2017-05-25","cited_by_count":502},{"id":"1812.01187","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","created":"2018-12-04","cited_by_count":431},{"id":"1905.12022","title":"Bayesian Nonparametric Federated Learning of Neural Networks","created":"2019-05-28","cited_by_count":387},{"id":"1707.08819","title":"A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets","created":"2017-07-27","cited_by_count":377},{"id":"2003.10422","title":"A Unified Theory of Decentralized SGD with Changing Topology and Local Updates","created":"2020-03-23","cited_by_count":367},{"id":"1805.11604","title":"How Does Batch Normalization Help Optimization?","created":"2018-05-29","cited_by_count":357},{"id":"2010.01264","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","created":"2020-10-03","cited_by_count":337},{"id":"1912.02365","title":"Lower Bounds for Non-Convex Stochastic Optimization","created":"2019-12-05","cited_by_count":307},{"id":"1910.00189","title":"The Non-IID Data Quagmire of Decentralized Machine Learning","created":"2019-10-01","cited_by_count":305},{"id":"2007.13518","title":"FedML: A Research Library and Benchmark for Federated Machine Learning","created":"2020-07-27","cited_by_count":300},{"id":"2006.04884","title":"On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines","created":"2020-06-08","cited_by_count":255},{"id":"1902.00340","title":"Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication","created":"2019-02-01","cited_by_count":221},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"1905.03817","title":"On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization","created":"2019-05-09","cited_by_count":180},{"id":"1910.06378","title":"SCAFFOLD: Stochastic Controlled Averaging for Federated Learning","created":"2019-10-14","cited_by_count":175},{"id":"1404.6264","title":"EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization","created":"2014-04-24","cited_by_count":160},{"id":"2007.01154","title":"Federated Learning with Compression: Unified Analysis and Sharp Guarantees","created":"2020-07-02","cited_by_count":160},{"id":"1710.06952","title":"Asynchronous Decentralized Parallel Stochastic Gradient Descent","created":"2017-10-18","cited_by_count":159},{"id":"2008.03606","title":"Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning","created":"2020-08-08","cited_by_count":154},{"id":"1811.10792","title":"Stochastic Gradient Push for Distributed Deep Learning","created":"2018-11-27","cited_by_count":152},{"id":"1803.07068","title":"D$^2$: Decentralized Training over Decentralized Data","created":"2018-03-19","cited_by_count":140},{"id":"1709.08765","title":"Network Topology and Communication-Computation Tradeoffs in Decentralized Optimization","created":"2017-09-26","cited_by_count":122},{"id":"1910.00643","title":"SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum","created":"2019-10-01","cited_by_count":121},{"id":"1810.12281","title":"Three Mechanisms of Weight Decay Regularization","created":"2018-10-29","cited_by_count":113},{"id":"1907.09356","title":"Decentralized Deep Learning with Arbitrary Communication Compression","created":"2019-07-22","cited_by_count":111},{"id":"1805.11454","title":"Distributed Stochastic Gradient Tracking Methods","created":"2018-05-25","cited_by_count":106},{"id":"1803.06443","title":"Communication Compression for Decentralized Training","created":"2018-03-17","cited_by_count":88},{"id":"1702.08704","title":"Optimal algorithms for smooth and strongly convex distributed optimization in networks","created":"2017-02-28","cited_by_count":83},{"id":"1905.09435","title":"MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Sampling","created":"2019-05-23","cited_by_count":67},{"id":"1803.01814","title":"Norm matters: efficient and accurate normalization schemes in deep networks","created":"2018-03-05","cited_by_count":62},{"id":"2008.07424","title":"Siloed Federated Learning for Multi-Centric Histopathology Datasets","created":"2020-08-17","cited_by_count":61},{"id":"1809.00846","title":"Towards Understanding Regularization in Batch Normalization","created":"2018-09-04","cited_by_count":56},{"id":"1808.10396","title":"A Unified Analysis of Stochastic Momentum Methods for Deep Learning","created":"2018-08-30","cited_by_count":55},{"id":"1810.06801","title":"Quasi-hyperbolic momentum and Adam for deep learning","created":"2018-10-16","cited_by_count":48},{"id":"1812.04529","title":"On the Ineffectiveness of Variance Reduced Optimization for Deep Learning","created":"2018-12-11","cited_by_count":48},{"id":"2012.04061","title":"Faster Non-Convex Federated Learning via Global and Local Momentum","created":"2020-12-07","cited_by_count":48},{"id":"2004.02967","title":"Evolving Normalization-Activation Layers","created":"2020-04-06","cited_by_count":45},{"id":"1910.13962","title":"Understanding the Role of Momentum in Stochastic Gradient Methods","created":"2019-10-30","cited_by_count":44},{"id":"1806.00291","title":"Optimal Algorithms for Non-Smooth Distributed Optimization in Networks","created":"2018-06-01","cited_by_count":41},{"id":"1804.00325","title":"Aggregated Momentum: Stability Through Passive Damping","created":"2018-04-01","cited_by_count":36},{"id":"1912.03194","title":"Why are Adaptive Methods Good for Attention Models?","created":"2019-12-06","cited_by_count":35},{"id":"2002.12688","title":"Decentralized gradient methods: does topology matter?","created":"2020-02-28","cited_by_count":35},{"id":"2008.01425","title":"PowerGossip: Practical Low-Rank Communication Compression in Decentralized Deep Learning","created":"2020-08-04","cited_by_count":35},{"id":"1903.10956","title":"On the Influence of Bias-Correction on Distributed Stochastic Optimization","created":"2019-03-26","cited_by_count":34},{"id":"1912.04230","title":"Variance-Reduced Decentralized Stochastic Optimization with Accelerated Convergence","created":"2019-12-09","cited_by_count":33},{"id":"2005.07041","title":"SQuARM-SGD: Communication-Efficient Momentum SGD for Decentralized Optimization","created":"2020-05-13","cited_by_count":31},{"id":"2006.05720","title":"Extrapolation for Large-batch Training in Deep Learning","created":"2020-06-10","cited_by_count":25},{"id":"2002.09964","title":"Quantized Decentralized Stochastic Learning over Directed Graphs","created":"2020-02-23","cited_by_count":24},{"id":"2002.11787","title":"Moniqua: Modulo Quantized Communication in Decentralized SGD","created":"2020-02-26","cited_by_count":24},{"id":"2010.11166","title":"Decentralized Deep Learning using Momentum-Accelerated Consensus","created":"2020-10-21","cited_by_count":14},{"id":"1810.02660","title":"Accelerated Decentralized Optimization with Local Updates for Smooth and Strongly Convex Objectives","created":"2018-10-05","cited_by_count":11},{"id":"1911.12665","title":"D-SPIDER-SFO: A Decentralized Optimization Algorithm with Faster Convergence Rate for Nonconvex Problems","created":"2019-11-28","cited_by_count":11},{"id":"2003.00816","title":"Can Primal Methods Outperform Primal-dual Methods in Decentralized Dynamic Optimization?","created":"2020-03-02","cited_by_count":11}],"next_cursor":null}