{"list":"other","total":106,"rows":[{"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":"1803.01498","title":"Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates","created":"2018-03-05","cited_by_count":711},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"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":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"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":"1803.00942","title":"Not All Samples Are Created Equal: Deep Learning with Importance Sampling","created":"2018-03-02","cited_by_count":328},{"id":"1910.00189","title":"The Non-IID Data Quagmire of Decentralized Machine Learning","created":"2019-10-01","cited_by_count":305},{"id":"1705.07878","title":"TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning","created":"2017-05-22","cited_by_count":256},{"id":"1809.10505","title":"The Convergence of Sparsified Gradient Methods","created":"2018-09-27","cited_by_count":229},{"id":"1902.00340","title":"Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication","created":"2019-02-01","cited_by_count":221},{"id":"1710.09854","title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","created":"2017-10-26","cited_by_count":201},{"id":"1807.05358","title":"Beyond Data and Model Parallelism for Deep Neural Networks","created":"2018-07-14","cited_by_count":179},{"id":"1812.08011","title":"Training Deep Neural Networks with 8-bit Floating Point Numbers","created":"2018-12-19","cited_by_count":164},{"id":"1404.6264","title":"EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization","created":"2014-04-24","cited_by_count":160},{"id":"1310.7063","title":"On the Convergence of Decentralized Gradient Descent","created":"2013-10-26","cited_by_count":159},{"id":"1710.06952","title":"Asynchronous Decentralized Parallel Stochastic Gradient Descent","created":"2017-10-18","cited_by_count":159},{"id":"1805.10559","title":"cpSGD: Communication-efficient and differentially-private distributed SGD","created":"2018-05-27","cited_by_count":158},{"id":"1802.09941","title":"Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis","created":"2018-02-26","cited_by_count":156},{"id":"1811.10792","title":"Stochastic Gradient Push for Distributed Deep Learning","created":"2018-11-27","cited_by_count":152},{"id":"1610.02132","title":"QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding","created":"2016-10-07","cited_by_count":147},{"id":"1603.06160","title":"Stochastic Variance Reduction for Nonconvex Optimization","created":"2016-03-19","cited_by_count":145},{"id":"1308.6594","title":"Mini-batch Stochastic Approximation Methods for Nonconvex Stochastic Composite Optimization","created":"2013-08-29","cited_by_count":143},{"id":"1805.11046","title":"Scalable Methods for 8-bit Training of Neural Networks","created":"2018-05-25","cited_by_count":142},{"id":"1803.07068","title":"D$^2$: Decentralized Training over Decentralized Data","created":"2018-03-19","cited_by_count":140},{"id":"1806.04090","title":"ATOMO: Communication-efficient Learning via Atomic Sparsification","created":"2018-06-11","cited_by_count":136},{"id":"1803.04311","title":"Deep Learning in Mobile and Wireless Networking: A Survey","created":"2018-03-12","cited_by_count":118},{"id":"1506.08272","title":"Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization","created":"2015-06-27","cited_by_count":116},{"id":"1805.10367","title":"Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization","created":"2018-05-25","cited_by_count":111},{"id":"1609.08326","title":"Asynchronous Stochastic Gradient Descent with Delay Compensation","created":"2016-09-27","cited_by_count":99},{"id":"1905.05957","title":"DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression","created":"2019-05-15","cited_by_count":99},{"id":"1802.03801","title":"SGD and Hogwild! Convergence Without the Bounded Gradients Assumption","created":"2018-02-11","cited_by_count":95},{"id":"1401.2753","title":"Stochastic Optimization with Importance Sampling","created":"2014-01-13","cited_by_count":91},{"id":"1412.6651","title":"Deep learning with Elastic Averaging SGD","created":"2014-12-20","cited_by_count":90},{"id":"1803.06443","title":"Communication Compression for Decentralized Training","created":"2018-03-17","cited_by_count":88},{"id":"1803.08917","title":"Byzantine Stochastic Gradient Descent","created":"2018-03-23","cited_by_count":81},{"id":"1810.08313","title":"Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD","created":"2018-10-19","cited_by_count":77},{"id":"1806.08054","title":"Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization","created":"2018-06-21","cited_by_count":76},{"id":"1803.09877","title":"DRACO: Byzantine-resilient Distributed Training via Redundant Gradients","created":"2018-03-27","cited_by_count":75},{"id":"1603.05643","title":"Variance Reduction for Faster Non-Convex Optimization","created":"2016-03-17","cited_by_count":72},{"id":"1806.10077","title":"Random Shuffling Beats SGD after Finite Epochs","created":"2018-06-26","cited_by_count":67},{"id":"1903.01463","title":"SGD without Replacement: Sharper Rates for General Smooth Convex Functions","created":"2019-03-04","cited_by_count":61},{"id":"1605.06398","title":"Stochastic Variance Reduction Methods for Saddle-Point Problems","created":"2016-05-20","cited_by_count":60},{"id":"1704.07807","title":"A decentralized proximal-gradient method with network independent step-sizes and separated convergence rates","created":"2017-04-25","cited_by_count":51},{"id":"1910.12166","title":"Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization","created":"2019-10-27","cited_by_count":47},{"id":"1606.00498","title":"A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order","created":"2016-06-01","cited_by_count":44},{"id":"1602.02101","title":"Variance-Reduced and Projection-Free Stochastic Optimization","created":"2016-02-05","cited_by_count":40},{"id":"1506.03662","title":"Variance Reduced Stochastic Gradient Descent with Neighbors","created":"2015-06-11","cited_by_count":39},{"id":"1506.01972","title":"Improved SVRG for Non-Strongly-Convex or Sum-of-Non-Convex Objectives","created":"2015-06-05","cited_by_count":38},{"id":"1605.07991","title":"Efficient Distributed Learning with Sparsity","created":"2016-05-25","cited_by_count":38},{"id":"1910.04956","title":"Central Server Free Federated Learning over Single-sided Trust Social Networks","created":"2019-10-11","cited_by_count":33},{"id":"1506.06438","title":"Taming the Wild: A Unified Analysis of Hogwild!-Style Algorithms","created":"2015-06-22","cited_by_count":31},{"id":"1910.07561","title":"A Double Residual Compression Algorithm for Efficient Distributed Learning","created":"2019-10-16","cited_by_count":31},{"id":"1808.04883","title":"COLA: Decentralized Linear Learning","created":"2018-08-13","cited_by_count":30},{"id":"1809.03054","title":"SEGA: Variance Reduction via Gradient Sketching","created":"2018-09-09","cited_by_count":29},{"id":"1811.03619","title":"Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training","created":"2018-11-08","cited_by_count":28},{"id":"1802.03475","title":"Communication-Computation Efficient Gradient Coding","created":"2018-02-09","cited_by_count":27},{"id":"1803.03288","title":"TicTac: Accelerating Distributed Deep Learning with Communication Scheduling","created":"2018-03-08","cited_by_count":27},{"id":"1311.1873","title":"An Asynchronous Parallel Stochastic Coordinate Descent Algorithm","created":"2013-11-08","cited_by_count":26},{"id":"1509.07728","title":"Online Stochastic Linear Optimization under One-bit Feedback","created":"2015-09-25","cited_by_count":26},{"id":"1711.04969","title":"Straggler Mitigation in Distributed Optimization Through Data Encoding","created":"2017-11-14","cited_by_count":26},{"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":"1403.3862","title":"Asynchronous Stochastic Coordinate Descent: Parallelism and Convergence Properties","created":"2014-03-15","cited_by_count":21},{"id":"1606.02421","title":"Gossip Dual Averaging for Decentralized Optimization of Pairwise Functions","created":"2016-06-08","cited_by_count":21},{"id":"1811.03617","title":"GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training","created":"2018-11-08","cited_by_count":21},{"id":"1905.03960","title":"Priority-based Parameter Propagation for Distributed DNN Training","created":"2019-05-10","cited_by_count":21},{"id":"1805.12591","title":"On Acceleration with Noise-Corrupted Gradients","created":"2018-05-31","cited_by_count":20},{"id":"1502.03508","title":"Adding vs. Averaging in Distributed Primal-Dual Optimization","created":"2015-02-12","cited_by_count":19},{"id":"1508.00882","title":"Asynchronous stochastic convex optimization","created":"2015-08-04","cited_by_count":19},{"id":"1707.03858","title":"Gradient Coding from Cyclic MDS Codes and Expander Graphs","created":"2017-07-12","cited_by_count":19},{"id":"1802.07389","title":"3LC: Lightweight and Effective Traffic Compression for Distributed Machine Learning","created":"2018-02-21","cited_by_count":16},{"id":"1705.08494","title":"Asynchronous Coordinate Descent under More Realistic Assumptions","created":"2017-05-20","cited_by_count":14},{"id":"1809.04146","title":"Nonconvex Variance Reduced Optimization with Arbitrary Sampling","created":"2018-09-11","cited_by_count":14},{"id":"1806.11027","title":"A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates","created":"2018-06-28","cited_by_count":11},{"id":"1812.05762","title":"Helix: Holistic Optimization for Accelerating Iterative Machine Learning","created":"2018-12-14","cited_by_count":11},{"id":"1910.05857","title":"Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: A Joint Gradient Estimation and Tracking Approach","created":"2019-10-13","cited_by_count":11},{"id":"1702.08169","title":"Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis","created":"2017-02-27","cited_by_count":10},{"id":"1802.04796","title":"Stochastic Variance-Reduced Cubic Regularized Newton Method","created":"2018-02-13","cited_by_count":10},{"id":"1610.06664","title":"Stochastic Gradient MCMC with Stale Gradients","created":"2016-10-21","cited_by_count":9},{"id":"1810.07766","title":"Distributed Learning over Unreliable Networks","created":"2018-10-17","cited_by_count":9},{"id":"1902.11259","title":"Distributed Learning with Sublinear Communication","created":"2019-02-28","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":"1610.00970","title":"Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure","created":"2016-10-04","cited_by_count":8},{"id":"1704.06735","title":"Asynchronous Distributed Variational Gaussian Processes for Regression","created":"2017-04-22","cited_by_count":8},{"id":"1801.06027","title":"In-RDBMS Hardware Acceleration of Advanced Analytics","created":"2018-01-08","cited_by_count":8},{"id":"1803.00841","title":"Gradient-based Sampling: An Adaptive Importance Sampling for Least-squares","created":"2018-03-02","cited_by_count":8},{"id":"1802.04791","title":"Stochastic Variance-Reduced Hamilton Monte Carlo Methods","created":"2018-02-13","cited_by_count":7},{"id":"1802.05811","title":"Distributed Stochastic Optimization via Adaptive SGD","created":"2018-02-16","cited_by_count":7},{"id":"1802.07928","title":"Asynchronous Byzantine Machine Learning (the case of SGD)","created":"2018-02-22","cited_by_count":7},{"id":"1803.01302","title":"Distributed Nonparametric Regression under Communication Constraints","created":"2018-03-04","cited_by_count":7},{"id":"1605.02711","title":"Nonconvex Sparse Learning via Stochastic Optimization with Progressive Variance Reduction","created":"2016-05-09","cited_by_count":6},{"id":"1602.01716","title":"Decentralized Prediction-Correction Methods for Networked Time-Varying Convex Optimization","created":"2016-02-04","cited_by_count":5},{"id":"1605.09721","title":"CYCLADES: Conflict-free Asynchronous Machine Learning","created":"2016-05-31","cited_by_count":5},{"id":"1409.8547","title":"An Asynchronous Distributed Proximal Gradient Method for Composite Convex Optimization","created":"2014-09-30","cited_by_count":4},{"id":"1504.01365","title":"PASSCoDe: Parallel ASynchronous Stochastic dual Co-ordinate Descent","created":"2015-04-06","cited_by_count":4},{"id":"1703.09193","title":"A Cost-based Optimizer for Gradient Descent Optimization","created":"2017-03-27","cited_by_count":4},{"id":"1803.06333","title":"Snap ML: A Hierarchical Framework for Machine Learning","created":"2018-03-16","cited_by_count":4}],"next_cursor":"100"}