{"total":82,"rows":[{"id":"2102.04761","title":"Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data","created":"2021-02-09","cited_by_count":69,"area":null},{"id":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2302.14428","title":"Stochastic Gradient Descent under Markovian Sampling Schemes","created":"2023-02-28","cited_by_count":38,"area":null},{"id":"2103.03239","title":"Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices","created":"2021-03-04","cited_by_count":36,"area":null},{"id":"2105.08023","title":"Removing Data Heterogeneity Influence Enhances Network Topology Dependence of Decentralized SGD","created":"2021-05-17","cited_by_count":29,"area":null},{"id":"2206.05091","title":"Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging","created":"2022-06-10","cited_by_count":27,"area":null},{"id":"2105.09080","title":"Accelerating Gossip SGD with Periodic Global Averaging","created":"2021-05-19","cited_by_count":25,"area":null},{"id":"2106.08315","title":"Decentralized Local Stochastic Extra-Gradient for Variational Inequalities","created":"2021-06-15","cited_by_count":25,"area":null},{"id":"2210.07881","title":"Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate","created":"2022-10-14","cited_by_count":25,"area":null},{"id":"2210.07863","title":"Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization","created":"2022-10-14","cited_by_count":23,"area":null},{"id":"2106.04469","title":"Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization Over Time-Varying Networks","created":"2021-06-08","cited_by_count":19,"area":null},{"id":"2207.03957","title":"Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with Inexact Prox","created":"2022-07-08","cited_by_count":19,"area":null},{"id":"2501.16168","title":"Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity","created":"2025-01-27","cited_by_count":18,"area":null},{"id":"2110.12347","title":"Acceleration in Distributed Optimization under Similarity","created":"2021-10-24","cited_by_count":17,"area":null},{"id":"2306.14853","title":"Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles","created":"2023-06-26","cited_by_count":17,"area":null},{"id":"2111.04287","title":"BlueFog: Make Decentralized Algorithms Practical for Optimization and Deep Learning","created":"2021-11-08","cited_by_count":16,"area":null},{"id":"2112.15199","title":"Accelerated Primal-Dual Gradient Method for Smooth and Convex-Concave Saddle-Point Problems with Bilinear Coupling","created":"2021-12-30","cited_by_count":16,"area":null},{"id":"2303.10695","title":"On the Convergence of Decentralized Federated Learning Under Imperfect Information Sharing","created":"2023-03-19","cited_by_count":16,"area":null},{"id":"2106.07644","title":"A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip","created":"2021-06-10","cited_by_count":15,"area":null},{"id":"2101.02696","title":"Accelerated, Optimal, and Parallel: Some Results on Model-Based Stochastic Optimization","created":"2021-01-07","cited_by_count":14,"area":null},{"id":"2202.02771","title":"Optimal Algorithms for Decentralized Stochastic Variational Inequalities","created":"2022-02-06","cited_by_count":14,"area":null},{"id":"2305.16297","title":"Unbiased Compression Saves Communication in Distributed Optimization: When and How Much?","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2102.09234","title":"ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks","created":"2021-02-18","cited_by_count":13,"area":null},{"id":"2205.13170","title":"Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost","created":"2022-05-26","cited_by_count":13,"area":null},{"id":"2204.06477","title":"Data-heterogeneity-aware Mixing for Decentralized Learning","created":"2022-04-13","cited_by_count":12,"area":null},{"id":"2104.02596","title":"Accelerated Gradient Tracking over Time-varying Graphs for Decentralized Optimization","created":"2021-04-06","cited_by_count":11,"area":null},{"id":"2207.03730","title":"Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology","created":"2022-07-08","cited_by_count":10,"area":null},{"id":"2503.14353","title":"Unified Analysis of Decentralized Gradient Descent: a Contraction Mapping Framework","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2102.07214","title":"Communication-Efficient Distributed Optimization with Quantized Preconditioners","created":"2021-02-14","cited_by_count":8,"area":null},{"id":"2107.10706","title":"Distributed Saddle-Point Problems Under Similarity","created":"2021-07-22","cited_by_count":8,"area":null},{"id":"2208.00779","title":"DADAO: Decoupled Accelerated Decentralized Asynchronous Optimization","created":"2022-07-26","cited_by_count":8,"area":null},{"id":"2402.09173","title":"Optimal and Efficient Algorithms for Decentralized Online Convex Optimization","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2402.10001","title":"Privacy Attacks in Decentralized Learning","created":"2024-02-15","cited_by_count":8,"area":null},{"id":"2410.10418","title":"Unified Breakdown Analysis for Byzantine Robust Gossip","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2108.04448","title":"Decentralized Composite Optimization with Compression","created":"2021-08-10","cited_by_count":7,"area":null},{"id":"2306.08289","title":"$\\textbf{A}^2\\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning","created":"2023-06-14","cited_by_count":7,"area":null},{"id":"2306.11201","title":"Adaptive Federated Learning with Auto-Tuned Clients","created":"2023-06-19","cited_by_count":7,"area":null},{"id":"2209.07446","title":"Efficiency Ordering of Stochastic Gradient Descent","created":"2022-09-15","cited_by_count":6,"area":null},{"id":"2212.02387","title":"An Efficient Stochastic Algorithm for Decentralized Nonconvex-Strongly-Concave Minimax Optimization","created":"2022-12-05","cited_by_count":6,"area":null},{"id":"2103.13147","title":"Multi-Agent Off-Policy TD Learning: Finite-Time Analysis with Near-Optimal Sample Complexity and Communication Complexity","created":"2021-03-24","cited_by_count":5,"area":null},{"id":"2106.07289","title":"Decentralized Personalized Federated Learning for Min-Max Problems","created":"2021-06-14","cited_by_count":4,"area":null},{"id":"2205.06331","title":"Collaborative Multi-agent Stochastic Linear Bandits","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2211.00533","title":"Optimal Complexity in Non-Convex Decentralized Learning over Time-Varying Networks","created":"2022-11-01","cited_by_count":4,"area":null},{"id":"2406.00621","title":"Log-Scale Quantization in Distributed First-Order Methods: Gradient-based Learning from Distributed Data","created":"2024-06-02","cited_by_count":4,"area":null},{"id":"2102.06280","title":"Straggler-Resilient Distributed Machine Learning with Dynamic Backup Workers","created":"2021-02-11","cited_by_count":3,"area":null},{"id":"2106.03585","title":"Asynchronous speedup in decentralized optimization","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2201.11183","title":"A dual approach for federated learning","created":"2022-01-26","cited_by_count":3,"area":null},{"id":"2202.05812","title":"Distributed saddle point problems for strongly concave-convex functions","created":"2022-02-11","cited_by_count":3,"area":null},{"id":"2306.06559","title":"Straggler-Resilient Decentralized Learning via Adaptive Asynchronous Updates","created":"2023-06-11","cited_by_count":3,"area":null},{"id":"2203.05117","title":"Optimal Methods for Convex Risk Averse Distributed Optimization","created":"2022-03-10","cited_by_count":2,"area":null},{"id":"2204.12663","title":"Understanding A Class of Decentralized and Federated Optimization Algorithms: A Multi-Rate Feedback Control Perspective","created":"2022-04-27","cited_by_count":2,"area":null},{"id":"2312.11861","title":"A Proximal Gradient Method With Probabilistic Multi-Gossip Communications for Decentralized Composite Optimization","created":"2023-12-19","cited_by_count":2,"area":null},{"id":"2402.02569","title":"On the Complexity of Finite-Sum Smooth Optimization under the Polyak-{\\L}ojasiewicz Condition","created":"2024-02-04","cited_by_count":2,"area":null},{"id":"2410.17382","title":"Cooperative Multi-Agent Constrained Stochastic Linear Bandits","created":"2024-10-22","cited_by_count":2,"area":null},{"id":"2107.12065","title":"Provably Accelerated Decentralized Gradient Method Over Unbalanced Directed Graphs","created":"2021-07-26","cited_by_count":1,"area":null},{"id":"2309.13307","title":"CORE: Common Random Reconstruction for Distributed Optimization with Provable Low Communication Complexity","created":"2023-09-23","cited_by_count":1,"area":null},{"id":"2310.07983","title":"Achieving Linear Speedup with ProxSkip in Distributed Stochastic Optimization","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2405.03449","title":"Byzantine-Robust Gossip: Insights from a Dual Approach","created":"2024-05-06","cited_by_count":1,"area":null},{"id":"2405.18031","title":"Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2407.01283","title":"Energy-Aware Decentralized Learning with Intermittent Model Training","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2410.06482","title":"OledFL: Unleashing the Potential of Decentralized Federated Learning via Opposite Lookahead Enhancement","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2501.03222","title":"Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization","created":"2025-01-06","cited_by_count":1,"area":null},{"id":"2506.05791","title":"Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2601.07021","title":"Tight Analysis of Decentralized SGD: A Markov Chain Perspective","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2601.11435","title":"Near-Optimal Decentralized Stochastic Nonconvex Optimization with Heavy-Tailed Noise","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2606.07496","title":"Accelerated Decentralized Stochastic Gradient Descent for Strongly Convex Optimization","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2110.15283","title":"Decentralized Feature-Distributed Optimization for Generalized Linear Models","created":"2021-10-28","cited_by_count":0,"area":null},{"id":"2304.11788","title":"Can Decentralized Stochastic Minimax Optimization Algorithms Converge Linearly for Finite-Sum Nonconvex-Nonconcave Problems?","created":"2023-04-24","cited_by_count":0,"area":null},{"id":"2306.06715","title":"FedDec: Peer-to-peer Aided Federated Learning","created":"2023-06-11","cited_by_count":0,"area":null},{"id":"2311.05760","title":"Compressed and Sparse Models for Non-Convex Decentralized Learning","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2312.04719","title":"Distributed Optimization via Kernelized Multi-armed Bandits","created":"2023-12-07","cited_by_count":0,"area":null},{"id":"2407.02689","title":"Accelerating Distributed Optimization: A Primal-Dual Perspective on Local Steps","created":"2024-07-02","cited_by_count":0,"area":null},{"id":"2504.17471","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2506.08362","title":"Solving Convex-Concave Problems with $\\tilde{\\mathcal{O}}(\\epsilon^{-4/7})$ Second-Order Oracle Complexity","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2509.08726","title":"Decentralized Stochastic Nonconvex Optimization under the $(L_0,L_1)$-Smoothness","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2602.11789","title":"Decentralized Non-convex Stochastic Optimization with Heterogeneous Variance","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2602.16148","title":"Local adapt-then-combine algorithms for distributed nonsmooth optimization: Achieving provable communication acceleration","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2606.03209","title":"DECA: Decentralizing Block-Wise Adam for Efficient LLM Full-Parameter Fine-Tuning on Non-IID Data","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.04399","title":"DPDL: Towards Differential Privacy Preservation in Decentralized Stochastic Learning on Non-IID Data","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.04757","title":"Near-Optimal Decentralized Stochastic Convex Optimization over Networks","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.04254","title":"Air-Plan: Query-Optimized Topology Selection for Over-the-Air Decentralized Federated Learning","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2609.33021","title":"Decentralized Optimization with Cross-Coupled Mixed Affine Constraints","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}