{"list":"other","total":62,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"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":"1712.01887","title":"Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training","created":"2017-12-05","cited_by_count":478},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"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":"1807.01695","title":"SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator","created":"2018-07-04","cited_by_count":287},{"id":"1705.07878","title":"TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning","created":"2017-05-22","cited_by_count":256},{"id":"1905.13727","title":"PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization","created":"2019-05-31","cited_by_count":238},{"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":"1906.02367","title":"Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computations","created":"2019-06-06","cited_by_count":181},{"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":"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":"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":"2002.12410","title":"On Biased Compression for Distributed Learning","created":"2020-02-27","cited_by_count":140},{"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":"1905.05957","title":"DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression","created":"2019-05-15","cited_by_count":99},{"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":"1803.06443","title":"Communication Compression for Decentralized Training","created":"2018-03-17","cited_by_count":88},{"id":"2102.07845","title":"MARINA: Faster Non-Convex Distributed Learning with Compression","created":"2021-02-15","cited_by_count":78},{"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":"1904.05115","title":"Stochastic Distributed Learning with Gradient Quantization and Variance Reduction","created":"2019-04-10","cited_by_count":65},{"id":"1506.01900","title":"Communication Complexity of Distributed Convex Learning and Optimization","created":"2015-06-05","cited_by_count":60},{"id":"2006.08085","title":"Optimal Complexity in Decentralized Training","created":"2020-06-15","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":"1801.02982","title":"How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD","created":"2018-01-08","cited_by_count":57},{"id":"2110.13363","title":"Exponential Graph is Provably Efficient for Decentralized Deep Training","created":"2021-10-26","cited_by_count":56},{"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":"2108.00951","title":"Rethinking gradient sparsification as total error minimization","created":"2021-08-02","cited_by_count":41},{"id":"2201.13320","title":"BEER: Fast $O(1/T)$ Rate for Decentralized Nonconvex Optimization with Communication Compression","created":"2022-01-31","cited_by_count":41},{"id":"2104.11981","title":"DecentLaM: Decentralized Momentum SGD for Large-batch Deep Training","created":"2021-04-24","cited_by_count":40},{"id":"1902.04686","title":"The Complexity of Making the Gradient Small in Stochastic Convex Optimization","created":"2019-02-13","cited_by_count":34},{"id":"2105.08023","title":"Removing Data Heterogeneity Influence Enhances Network Topology Dependence of Decentralized SGD","created":"2021-05-17","cited_by_count":29},{"id":"2007.13221","title":"CSER: Communication-efficient SGD with Error Reset","created":"2020-07-26","cited_by_count":27},{"id":"2202.00998","title":"3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation","created":"2022-02-02","cited_by_count":27},{"id":"2105.09080","title":"Accelerating Gossip SGD with Periodic Global Averaging","created":"2021-05-19","cited_by_count":25},{"id":"2007.00232","title":"Linear Convergent Decentralized Optimization with Compression","created":"2020-07-01","cited_by_count":22},{"id":"2102.12528","title":"Preserved central model for faster bidirectional compression in distributed settings","created":"2021-02-24","cited_by_count":21},{"id":"1901.11224","title":"Lower Bounds for Smooth Nonconvex Finite-Sum Optimization","created":"2019-01-31","cited_by_count":20},{"id":"1811.01903","title":"Lower Bounds for Parallel and Randomized Convex Optimization","created":"2018-11-05","cited_by_count":17},{"id":"2202.01268","title":"DASHA: Distributed Nonconvex Optimization with Communication Compression, Optimal Oracle Complexity, and No Client Synchronization","created":"2022-02-02","cited_by_count":16},{"id":"1410.0723","title":"A Lower Bound for the Optimization of Finite Sums","created":"2014-10-02","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":"1810.05291","title":"signSGD with Majority Vote is Communication Efficient And Fault Tolerant","created":"2018-10-11","cited_by_count":11},{"id":"2008.05823","title":"Step-Ahead Error Feedback for Distributed Training with Compressed Gradient","created":"2020-08-13","cited_by_count":9}],"next_cursor":null}