{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1806.00582","title":"Federated Learning with Non-IID Data","created":"2018-06-02","cited_by_count":1108},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"2003.14053","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","created":"2020-03-31","cited_by_count":712},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"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":"2003.10422","title":"A Unified Theory of Decentralized SGD with Changing Topology and Local Updates","created":"2020-03-23","cited_by_count":367},{"id":"2104.07586","title":"See through Gradients: Image Batch Recovery via GradInversion","created":"2021-04-15","cited_by_count":326},{"id":"1906.04893","title":"Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks","created":"2019-06-12","cited_by_count":293},{"id":"1810.02032","title":"Gradient descent aligns the layers of deep linear networks","created":"2018-10-04","cited_by_count":182},{"id":"2006.06914","title":"Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses","created":"2020-06-12","cited_by_count":173},{"id":"1404.6264","title":"EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization","created":"2014-04-24","cited_by_count":160},{"id":"1710.06952","title":"Asynchronous Decentralized Parallel Stochastic Gradient Descent","created":"2017-10-18","cited_by_count":159},{"id":"1811.10792","title":"Stochastic Gradient Push for Distributed Deep Learning","created":"2018-11-27","cited_by_count":152},{"id":"1810.07288","title":"Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron","created":"2018-10-16","cited_by_count":143},{"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":"2006.08157","title":"Fine-Grained Analysis of Stability and Generalization for Stochastic Gradient Descent","created":"2020-06-15","cited_by_count":119},{"id":"2002.10365","title":"The Early Phase of Neural Network Training","created":"2020-02-24","cited_by_count":115},{"id":"1703.01678","title":"Data-Dependent Stability of Stochastic Gradient Descent","created":"2017-03-05","cited_by_count":92},{"id":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84},{"id":"2206.00187","title":"DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training","created":"2022-06-01","cited_by_count":74},{"id":"1905.09435","title":"MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Sampling","created":"2019-05-23","cited_by_count":67},{"id":"2006.08085","title":"Optimal Complexity in Decentralized Training","created":"2020-06-15","cited_by_count":60},{"id":"2110.13363","title":"Exponential Graph is Provably Efficient for Decentralized Deep Training","created":"2021-10-26","cited_by_count":56},{"id":"1804.01619","title":"Stability and Convergence Trade-off of Iterative Optimization Algorithms","created":"2018-04-04","cited_by_count":53},{"id":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49},{"id":"2012.06244","title":"The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks","created":"2020-12-11","cited_by_count":46},{"id":"2110.09993","title":"A Unified and Refined Convergence Analysis for Non-Convex Decentralized Learning","created":"2021-10-19","cited_by_count":44},{"id":"2010.13988","title":"Toward Better Generalization Bounds with Locally Elastic Stability","created":"2020-10-27","cited_by_count":42},{"id":"2012.10931","title":"Recent advances in deep learning theory","created":"2020-12-20","cited_by_count":41},{"id":"1702.08712","title":"Algorithmic stability and hypothesis complexity","created":"2017-02-28","cited_by_count":39},{"id":"2110.04175","title":"RelaySum for Decentralized Deep Learning on Heterogeneous Data","created":"2021-10-08","cited_by_count":39},{"id":"1910.12308","title":"Asynchronous Decentralized SGD with Quantized and Local Updates","created":"2019-10-27","cited_by_count":36},{"id":"2111.13394","title":"Non-IID data and Continual Learning processes in Federated Learning: A long road ahead","created":"2021-11-26","cited_by_count":36},{"id":"1903.10956","title":"On the Influence of Bias-Correction on Distributed Stochastic Optimization","created":"2019-03-26","cited_by_count":34},{"id":"2201.11380","title":"Achieving Personalized Federated Learning with Sparse Local Models","created":"2022-01-27","cited_by_count":31},{"id":"2005.02426","title":"Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks","created":"2020-05-05","cited_by_count":27},{"id":"2206.03093","title":"Beyond spectral gap: The role of the topology in decentralized learning","created":"2022-06-07","cited_by_count":27},{"id":"2002.09964","title":"Quantized Decentralized Stochastic Learning over Directed Graphs","created":"2020-02-23","cited_by_count":24},{"id":"1904.04755","title":"Hypothesis Set Stability and Generalization","created":"2019-04-09","cited_by_count":23},{"id":"2111.04287","title":"BlueFog: Make Decentralized Algorithms Practical for Optimization and Deep Learning","created":"2021-11-08","cited_by_count":16},{"id":"1809.06958","title":"Graph-Dependent Implicit Regularisation for Distributed Stochastic Subgradient Descent","created":"2018-09-18","cited_by_count":14},{"id":"1503.00623","title":"Unregularized Online Learning Algorithms with General Loss Functions","created":"2015-03-02","cited_by_count":11},{"id":"1907.05701","title":"A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition","created":"2019-07-10","cited_by_count":6},{"id":"2112.01433","title":"Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent","created":"2021-12-02","cited_by_count":3}],"next_cursor":null}