{"list":"other","total":92,"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":"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":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"1603.04467","title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","created":"2016-03-14","cited_by_count":664},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"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":"1407.0202","title":"SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives","created":"2014-07-01","cited_by_count":402},{"id":"1901.09401","title":"SGD: General Analysis and Improved Rates","created":"2019-01-27","cited_by_count":207},{"id":"1310.7063","title":"On the Convergence of Decentralized Gradient Descent","created":"2013-10-26","cited_by_count":159},{"id":"1607.03218","title":"Achieving Geometric Convergence for Distributed Optimization over Time-Varying Graphs","created":"2016-07-12","cited_by_count":150},{"id":"1312.7853","title":"Communication Efficient Distributed Optimization using an Approximate Newton-type Method","created":"2013-12-30","cited_by_count":132},{"id":"2007.07989","title":"An Improved Analysis of Stochastic Gradient Descent with Momentum","created":"2020-07-15","cited_by_count":119},{"id":"1703.04782","title":"Online Learning Rate Adaptation with Hypergradient Descent","created":"2017-03-14","cited_by_count":118},{"id":"2006.05988","title":"Random Reshuffling: Simple Analysis with Vast Improvements","created":"2020-06-10","cited_by_count":115},{"id":"1306.2119","title":"Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)","created":"2013-06-10","cited_by_count":111},{"id":"1707.06386","title":"Bridging the Gap between Constant Step Size Stochastic Gradient Descent and Markov Chains","created":"2017-07-20","cited_by_count":88},{"id":"2004.00773","title":"A Blockchain-based Decentralized Federated Learning Framework with Committee Consensus","created":"2020-04-02","cited_by_count":84},{"id":"1510.08560","title":"Why Random Reshuffling Beats Stochastic Gradient Descent","created":"2015-10-29","cited_by_count":79},{"id":"1912.13163","title":"Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks","created":"2019-12-27","cited_by_count":79},{"id":"1610.05202","title":"Decentralized Collaborative Learning of Personalized Models over Networks","created":"2016-10-17","cited_by_count":76},{"id":"1610.08637","title":"Statistical Inference for Model Parameters in Stochastic Gradient Descent","created":"2016-10-27","cited_by_count":71},{"id":"1904.12838","title":"The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares","created":"2019-04-29","cited_by_count":68},{"id":"2004.04719","title":"On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration","created":"2020-04-09","cited_by_count":68},{"id":"1705.08435","title":"Personalized and Private Peer-to-Peer Machine Learning","created":"2017-05-23","cited_by_count":54},{"id":"1706.05507","title":"Variants of RMSProp and Adagrad with Logarithmic Regret Bounds","created":"2017-06-17","cited_by_count":50},{"id":"1712.09677","title":"Momentum and Stochastic Momentum for Stochastic Gradient, Newton, Proximal Point and Subspace Descent Methods","created":"2017-12-27","cited_by_count":49},{"id":"1810.06801","title":"Quasi-hyperbolic momentum and Adam for deep learning","created":"2018-10-16","cited_by_count":48},{"id":"2006.07904","title":"An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias","created":"2020-06-14","cited_by_count":48},{"id":"1709.03528","title":"GIANT: Globally Improved Approximate Newton Method for Distributed Optimization","created":"2017-09-11","cited_by_count":44},{"id":"1910.13962","title":"Understanding the Role of Momentum in Stochastic Gradient Methods","created":"2019-10-30","cited_by_count":44},{"id":"1306.5362","title":"A Statistical Perspective on Algorithmic Leveraging","created":"2013-06-23","cited_by_count":39},{"id":"1605.07991","title":"Efficient Distributed Learning with Sparsity","created":"2016-05-25","cited_by_count":38},{"id":"1901.09335","title":"Augment your batch: better training with larger batches","created":"2019-01-27","cited_by_count":37},{"id":"2002.03979","title":"Online Covariance Matrix Estimation in Stochastic Gradient Descent","created":"2020-02-10","cited_by_count":37},{"id":"1910.12308","title":"Asynchronous Decentralized SGD with Quantized and Local Updates","created":"2019-10-27","cited_by_count":36},{"id":"1611.09726","title":"Gossip training for deep learning","created":"2016-11-29","cited_by_count":35},{"id":"1605.04131","title":"Barzilai-Borwein Step Size for Stochastic Gradient Descent","created":"2016-05-13","cited_by_count":33},{"id":"1606.07365","title":"Parallel SGD: When does averaging help?","created":"2016-06-23","cited_by_count":32},{"id":"1906.04870","title":"Communication-Efficient Accurate Statistical Estimation","created":"2019-06-12","cited_by_count":32},{"id":"1702.01166","title":"Optimal Subsampling for Large Sample Logistic Regression","created":"2017-02-03","cited_by_count":29},{"id":"2002.12414","title":"On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings","created":"2020-02-27","cited_by_count":27},{"id":"1705.07176","title":"Accelerated Distributed Nesterov Gradient Descent","created":"2017-05-19","cited_by_count":25},{"id":"1901.05134","title":"DINGO: Distributed Newton-Type Method for Gradient-Norm Optimization","created":"2019-01-16","cited_by_count":20},{"id":"1907.05550","title":"Faster Neural Network Training with Data Echoing","created":"2019-07-12","cited_by_count":20},{"id":"2006.02409","title":"On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs","created":"2020-06-03","cited_by_count":19},{"id":"2109.09142","title":"Decentralized Wireless Federated Learning with Differential Privacy","created":"2021-09-19","cited_by_count":18},{"id":"1810.08264","title":"Quantile Regression Under Memory Constraint","created":"2018-10-18","cited_by_count":17},{"id":"1811.11368","title":"First-order Newton-type Estimator for Distributed Estimation and Inference","created":"2018-11-28","cited_by_count":16},{"id":"1407.2724","title":"On the Optimality of Averaging in Distributed Statistical Learning","created":"2014-07-10","cited_by_count":15},{"id":"1909.05784","title":"HHHFL: Hierarchical Heterogeneous Horizontal Federated Learning for Electroencephalography","created":"2019-09-11","cited_by_count":15},{"id":"1710.04753","title":"A Robust Accelerated Optimization Algorithm for Strongly Convex Functions","created":"2017-10-13","cited_by_count":14},{"id":"1811.11922","title":"Distributed Inference for Linear Support Vector Machine","created":"2018-11-29","cited_by_count":13},{"id":"2005.10435","title":"Optimal Distributed Subsampling for Maximum Quasi-Likelihood Estimators with Massive Data","created":"2020-05-21","cited_by_count":13},{"id":"2111.06328","title":"Stationary Behavior of Constant Stepsize SGD Type Algorithms: An Asymptotic Characterization","created":"2021-11-11","cited_by_count":13},{"id":"1906.05741","title":"Distributed High-dimensional Regression Under a Quantile Loss Function","created":"2019-06-13","cited_by_count":12},{"id":"1511.01443","title":"A Distributed One-Step Estimator","created":"2015-11-04","cited_by_count":11},{"id":"1701.06088","title":"Distributed inference for quantile regression processes","created":"2017-01-21","cited_by_count":11},{"id":"1710.10382","title":"Information-Based Optimal Subdata Selection for Big Data Linear Regression","created":"2017-10-28","cited_by_count":11},{"id":"1806.06761","title":"Optimal Subsampling Algorithms for Big Data Regressions","created":"2018-06-18","cited_by_count":11},{"id":"2001.10168","title":"Optimal subsampling for quantile regression in big data","created":"2020-01-28","cited_by_count":9},{"id":"2007.00360","title":"Decentralised Learning with Random Features and Distributed Gradient Descent","created":"2020-07-01","cited_by_count":9},{"id":"2305.17665","title":"Acceleration of stochastic gradient descent with momentum by averaging: finite-sample rates and asymptotic normality","created":"2023-05-28","cited_by_count":9},{"id":"1810.07211","title":"A Subsampling Line-Search Method with Second-Order Results","created":"2018-10-16","cited_by_count":8},{"id":"1908.04904","title":"Least Squares Approximation for a Distributed System","created":"2019-08-14","cited_by_count":8},{"id":"2110.13113","title":"Communication-Constrained Distributed Quantile Regression with Optimal Statistical Guarantees","created":"2021-10-25","cited_by_count":8},{"id":"1802.02698","title":"More Efficient Estimation for Logistic Regression with Optimal Subsample","created":"2018-02-08","cited_by_count":7},{"id":"1910.02986","title":"A Distributed and Integrated Method of Moments for High-Dimensional Correlated Data Analysis","created":"2019-10-07","cited_by_count":7},{"id":"1508.01126","title":"A subsampled double bootstrap for massive data","created":"2015-08-05","cited_by_count":5},{"id":"1810.03035","title":"Characterizing Deep-Learning I/O Workloads in TensorFlow","created":"2018-10-06","cited_by_count":5},{"id":"1906.00506","title":"DAve-QN: A Distributed Averaged Quasi-Newton Method with Local Superlinear Convergence Rate","created":"2019-06-03","cited_by_count":5},{"id":"2007.14546","title":"MLR-SNet: Transferable LR Schedules for Heterogeneous Tasks","created":"2020-07-29","cited_by_count":5},{"id":"2205.08364","title":"Network Gradient Descent Algorithm for Decentralized Federated Learning","created":"2022-05-06","cited_by_count":5},{"id":"1601.06239","title":"Divide and Conquer Local Average Regression","created":"2016-01-23","cited_by_count":4},{"id":"1605.00933","title":"Decentralized Quasi-Newton Methods","created":"2016-05-03","cited_by_count":4},{"id":"1803.01370","title":"A Distributed Quasi-Newton Algorithm for Empirical Risk Minimization with Nonsmooth Regularization","created":"2018-03-04","cited_by_count":4},{"id":"1903.03810","title":"Distributed Feature Screening via Componentwise Debiasing","created":"2019-03-09","cited_by_count":4},{"id":"2202.05498","title":"Fast and Robust Sparsity Learning over Networks: A Decentralized Surrogate Median Regression Approach","created":"2022-02-11","cited_by_count":4},{"id":"1305.0087","title":"Quantile Regression for Large-scale Applications","created":"2013-05-01","cited_by_count":3},{"id":"2306.04111","title":"Quasi-Newton Updating for Large-Scale Distributed Learning","created":"2023-06-07","cited_by_count":2},{"id":"1905.09948","title":"Divide-and-Conquer Information-Based Optimal Subdata Selection Algorithm","created":"2019-05-23","cited_by_count":1},{"id":"2006.07924","title":"Estimation and Inference for Multi-Kink Quantile Regression","created":"2020-06-14","cited_by_count":1},{"id":"2110.00936","title":"A Sequential Addressing Subsampling Method for Massive Data Analysis under Memory Constraint","created":"2021-10-03","cited_by_count":1},{"id":"2111.01507","title":"An Asymptotic Analysis of Minibatch-Based Momentum Methods for Linear Regression Models","created":"2021-11-02","cited_by_count":1},{"id":"2209.13705","title":"An Overview of the Data-Loader Landscape: Comparative Performance Analysis","created":"2022-09-27","cited_by_count":1},{"id":"2302.07533","title":"Optimal Subsampling Bootstrap for Massive Data","created":"2023-02-15","cited_by_count":1},{"id":"2304.06231","title":"Subsampling and Jackknifing: A Practically Convenient Solution for Large Data Analysis with Limited Computational Resources","created":"2023-04-13","cited_by_count":1},{"id":"2306.10395","title":"Distributed Semi-Supervised Sparse Statistical Inference","created":"2023-06-17","cited_by_count":1}],"next_cursor":null}