{"list":"other","total":51,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"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":"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":"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":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"id":"1912.02365","title":"Lower Bounds for Non-Convex Stochastic Optimization","created":"2019-12-05","cited_by_count":307},{"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":"1710.09854","title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","created":"2017-10-26","cited_by_count":201},{"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":"1803.07068","title":"D$^2$: Decentralized Training over Decentralized Data","created":"2018-03-19","cited_by_count":140},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134},{"id":"2106.05203","title":"EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback","created":"2021-06-09","cited_by_count":133},{"id":"1710.11606","title":"Lower Bounds for Finding Stationary Points I","created":"2017-10-31","cited_by_count":126},{"id":"1901.09269","title":"Distributed Learning with Compressed Gradient Differences","created":"2019-01-26","cited_by_count":112},{"id":"1805.11454","title":"Distributed Stochastic Gradient Tracking Methods","created":"2018-05-25","cited_by_count":106},{"id":"1805.09965","title":"LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning","created":"2018-05-25","cited_by_count":96},{"id":"1905.10988","title":"Natural Compression for Distributed Deep Learning","created":"2019-05-27","cited_by_count":90},{"id":"2002.11364","title":"Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization","created":"2020-02-26","cited_by_count":90},{"id":"1702.08704","title":"Optimal algorithms for smooth and strongly convex distributed optimization in networks","created":"2017-02-28","cited_by_count":83},{"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":"2102.04761","title":"Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data","created":"2021-02-09","cited_by_count":69},{"id":"2202.03836","title":"An Improved Analysis of Gradient Tracking for Decentralized Machine Learning","created":"2022-02-08","cited_by_count":69},{"id":"1506.01900","title":"Communication Complexity of Distributed Convex Learning and Optimization","created":"2015-06-05","cited_by_count":60},{"id":"1711.00841","title":"Lower Bounds for Finding Stationary Points II: First-Order Methods","created":"2017-11-02","cited_by_count":58},{"id":"1806.06573","title":"Distributed learning with compressed gradients","created":"2018-06-18","cited_by_count":55},{"id":"2008.04195","title":"An improved convergence analysis for decentralized online stochastic non-convex optimization","created":"2020-08-10","cited_by_count":53},{"id":"2006.14591","title":"Bidirectional compression in heterogeneous settings for distributed or federated learning with partial participation: tight convergence guarantees","created":"2020-06-25","cited_by_count":46},{"id":"2002.08958","title":"Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal Compressor","created":"2020-02-20","cited_by_count":45},{"id":"2010.00091","title":"Error Compensated Distributed SGD Can Be Accelerated","created":"2020-09-30","cited_by_count":45},{"id":"2110.09993","title":"A Unified and Refined Convergence Analysis for Non-Convex Decentralized Learning","created":"2021-10-19","cited_by_count":44},{"id":"2104.11981","title":"DecentLaM: Decentralized Momentum SGD for Large-batch Deep Training","created":"2021-04-24","cited_by_count":40},{"id":"2006.11573","title":"Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization","created":"2020-06-20","cited_by_count":36},{"id":"1902.04686","title":"The Complexity of Making the Gradient Small in Stochastic Convex Optimization","created":"2019-02-13","cited_by_count":34},{"id":"1903.10956","title":"On the Influence of Bias-Correction on Distributed Stochastic Optimization","created":"2019-03-26","cited_by_count":34},{"id":"2206.03665","title":"Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression","created":"2022-06-08","cited_by_count":33},{"id":"2105.08023","title":"Removing Data Heterogeneity Influence Enhances Network Topology Dependence of Decentralized SGD","created":"2021-05-17","cited_by_count":29},{"id":"1908.08200","title":"RATQ: A Universal Fixed-Length Quantizer for Stochastic Optimization","created":"2019-08-22","cited_by_count":23},{"id":"2107.09461","title":"CANITA: Faster Rates for Distributed Convex Optimization with Communication Compression","created":"2021-07-20","cited_by_count":23},{"id":"2210.07863","title":"Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization","created":"2022-10-14","cited_by_count":23},{"id":"1811.01903","title":"Lower Bounds for Parallel and Randomized Convex Optimization","created":"2018-11-05","cited_by_count":17},{"id":"1410.0723","title":"A Lower Bound for the Optimization of Finite Sums","created":"2014-10-02","cited_by_count":13},{"id":"2102.09234","title":"ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks","created":"2021-02-18","cited_by_count":13},{"id":"2104.12112","title":"Improved Analysis and Rates for Variance Reduction under Without-replacement Sampling Orders","created":"2021-04-25","cited_by_count":13},{"id":"1808.03880","title":"Parallelization does not Accelerate Convex Optimization: Adaptivity Lower Bounds for Non-smooth Convex Minimization","created":"2018-08-12","cited_by_count":12},{"id":"2305.07612","title":"Lower Bounds and Accelerated Algorithms in Distributed Stochastic Optimization with Communication Compression","created":"2023-05-12","cited_by_count":11},{"id":"2211.00533","title":"Optimal Complexity in Non-Convex Decentralized Learning over Time-Varying Networks","created":"2022-11-01","cited_by_count":4}],"next_cursor":null}