{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"1909.06335","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","created":"2019-09-13","cited_by_count":851},{"id":"2111.04263","title":"Federated Learning Based on Dynamic Regularization","created":"2021-11-08","cited_by_count":562},{"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":"1902.00340","title":"Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication","created":"2019-02-01","cited_by_count":221},{"id":"2101.11203","title":"Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning","created":"2021-01-27","cited_by_count":193},{"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":"2006.04710","title":"The Lipschitz Constant of Self-Attention","created":"2020-06-08","cited_by_count":174},{"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":"1910.14425","title":"On the Convergence of Local Descent Methods in Federated Learning","created":"2019-10-31","cited_by_count":153},{"id":"1811.10792","title":"Stochastic Gradient Push for Distributed Deep Learning","created":"2018-11-27","cited_by_count":152},{"id":"2005.11418","title":"FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Data","created":"2020-05-22","cited_by_count":144},{"id":"2206.02618","title":"Generalized Federated Learning via Sharpness Aware Minimization","created":"2022-06-06","cited_by_count":144},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134},{"id":"2104.11375","title":"Decentralized Federated Averaging","created":"2021-04-23","cited_by_count":114},{"id":"2006.08907","title":"Robust Federated Learning: The Case of Affine Distribution Shifts","created":"2020-06-16","cited_by_count":102},{"id":"2203.11834","title":"Improving Generalization in Federated Learning by Seeking Flat Minima","created":"2022-03-22","cited_by_count":98},{"id":"2011.02828","title":"Local SGD: Unified Theory and New Efficient Methods","created":"2020-11-03","cited_by_count":88},{"id":"2106.10874","title":"FedCM: Federated Learning with Client-level Momentum","created":"2021-06-21","cited_by_count":77},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74},{"id":"1908.07782","title":"Decentralized Federated Learning: A Segmented Gossip Approach","created":"2019-08-21","cited_by_count":64},{"id":"2110.14216","title":"What Do We Mean by Generalization in Federated Learning?","created":"2021-10-27","cited_by_count":62},{"id":"2110.13363","title":"Exponential Graph is Provably Efficient for Decentralized Deep Training","created":"2021-10-26","cited_by_count":56},{"id":"2302.10429","title":"FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy","created":"2023-02-21","cited_by_count":49},{"id":"2305.11584","title":"Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape","created":"2023-05-19","cited_by_count":46},{"id":"2302.04083","title":"Improving the Model Consistency of Decentralized Federated Learning","created":"2023-02-08","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":"2206.12680","title":"Topology-aware Generalization of Decentralized SGD","created":"2022-06-25","cited_by_count":38},{"id":"2102.06489","title":"Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness","created":"2021-02-12","cited_by_count":37},{"id":"1903.10956","title":"On the Influence of Bias-Correction on Distributed Stochastic Optimization","created":"2019-03-26","cited_by_count":34},{"id":"2102.05274","title":"Stability of SGD: Tightness Analysis and Improved Bounds","created":"2021-02-10","cited_by_count":33},{"id":"2210.00960","title":"Stability Analysis and Generalization Bounds of Adversarial Training","created":"2022-10-03","cited_by_count":30},{"id":"2306.03824","title":"Understanding Generalization of Federated Learning via Stability: Heterogeneity Matters","created":"2023-06-06","cited_by_count":27},{"id":"2204.03529","title":"FedADMM: A Robust Federated Deep Learning Framework with Adaptivity to System Heterogeneity","created":"2022-04-07","cited_by_count":25},{"id":"2302.00620","title":"Local Exact-Diffusion for Decentralized Optimization and Learning","created":"2023-02-01","cited_by_count":24},{"id":"2308.00522","title":"Efficient Federated Learning via Local Adaptive Amended Optimizer with Linear Speedup","created":"2023-07-30","cited_by_count":23},{"id":"2005.02503","title":"Information-Theoretic Bounds on the Generalization Error and Privacy Leakage in Federated Learning","created":"2020-05-05","cited_by_count":21},{"id":"2210.04757","title":"On the Performance of Gradient Tracking with Local Updates","created":"2022-10-10","cited_by_count":21},{"id":"2306.05706","title":"Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization","created":"2023-06-09","cited_by_count":21},{"id":"2206.10713","title":"Beyond Uniform Lipschitz Condition in Differentially Private Optimization","created":"2022-06-21","cited_by_count":19},{"id":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15},{"id":"2302.11051","title":"Fusion of Global and Local Knowledge for Personalized Federated Learning","created":"2023-02-21","cited_by_count":14},{"id":"2210.02418","title":"Gradient Descent in the Absence of Global Lipschitz Continuity of the Gradients","created":"2022-10-05","cited_by_count":11},{"id":"2306.02939","title":"Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm","created":"2023-06-05","cited_by_count":10},{"id":"2112.15486","title":"Efficient and Reliable Overlay Networks for Decentralized Federated Learning","created":"2021-12-12","cited_by_count":9},{"id":"2303.10758","title":"Lower Generalization Bounds for GD and SGD in Smooth Stochastic Convex Optimization","created":"2023-03-19","cited_by_count":6},{"id":"2308.08290","title":"DFedADMM: Dual Constraints Controlled Model Inconsistency for Decentralized Federated Learning","created":"2023-08-16","cited_by_count":6}],"next_cursor":null}