{"total":30,"rows":[{"id":"2205.02215","title":"FedNest: Federated Bilevel, Minimax, and Compositional Optimization","created":"2022-05-04","cited_by_count":60,"area":null},{"id":"2101.05471","title":"Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration","created":"2021-01-14","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":"2205.05632","title":"On Distributed Adaptive Optimization with Gradient Compression","created":"2022-05-11","cited_by_count":19,"area":null},{"id":"2109.03194","title":"On the Convergence of Decentralized Adaptive Gradient Methods","created":"2021-09-07","cited_by_count":17,"area":null},{"id":"2207.02829","title":"Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods","created":"2022-07-06","cited_by_count":15,"area":null},{"id":"2205.14473","title":"Efficient-Adam: Communication-Efficient Distributed Adam","created":"2022-05-28","cited_by_count":11,"area":null},{"id":"2104.12676","title":"Solving a class of non-convex min-max games using adaptive momentum methods","created":"2021-04-26","cited_by_count":10,"area":null},{"id":"2406.02872","title":"Combinatorial Optimization with Automated Graph Neural Networks","created":"2024-06-05","cited_by_count":5,"area":null},{"id":"2503.08147","title":"FilmComposer: LLM-Driven Music Production for Silent Film Clips","created":"2025-03-11","cited_by_count":5,"area":null},{"id":"2109.14375","title":"Dynamic Regret Analysis for Online Meta-Learning","created":"2021-09-29","cited_by_count":4,"area":null},{"id":"2209.01608","title":"Dynamic Regret of Adaptive Gradient Methods for Strongly Convex Problems","created":"2022-09-04","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":"2410.11998","title":"From promise to practice: realizing high-performance decentralized training","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2510.01377","title":"DeMuon: A Decentralized Muon for Matrix Optimization over Graphs","created":"2025-10-01","cited_by_count":4,"area":null},{"id":"2404.08079","title":"DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models","created":"2024-04-11","cited_by_count":3,"area":null},{"id":"2412.06105","title":"Fully Distributed Online Training of Graph Neural Networks in Networked Systems","created":"2024-12-08","cited_by_count":3,"area":null},{"id":"2203.06798","title":"The Role of Local Steps in Local SGD","created":"2022-03-14","cited_by_count":2,"area":null},{"id":"2209.10105","title":"Distributed Online Non-convex Optimization with Composite Regret","created":"2022-09-21","cited_by_count":2,"area":null},{"id":"2211.04088","title":"A Penalty-Based Method for Communication-Efficient Decentralized Bilevel Programming","created":"2022-11-08","cited_by_count":2,"area":null},{"id":"2508.04950","title":"Compressed Decentralized Momentum Stochastic Gradient Methods for Nonconvex Optimization","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2510.07980","title":"Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2205.00473","title":"A Survey on Distributed Online Optimization and Game","created":"2022-05-01","cited_by_count":1,"area":null},{"id":"2306.06375","title":"Optimized Gradient Tracking for Decentralized Online Learning","created":"2023-06-10","cited_by_count":1,"area":null},{"id":"2408.09775","title":"Faster Adaptive Decentralized Learning Algorithms","created":"2024-08-19","cited_by_count":1,"area":null},{"id":"2306.01648","title":"Federated Multi-Sequence Stochastic Approximation with Local Hypergradient Estimation","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2508.20645","title":"A Hybrid Stochastic Gradient Tracking Method for Distributed Online Optimization Over Time-Varying Directed Networks","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2509.22174","title":"Efficiency Boost in Decentralized Optimization: Reimagining Neighborhood Aggregation with Minimal Overhead","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2602.17545","title":"Adaptive Decentralized Composite Optimization via Three-Operator Splitting","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2604.09970","title":"LoDAdaC: a unified local training-based decentralized framework with adaptive gradients and compressed communication","created":"2026-04-11","cited_by_count":0,"area":null}],"next_cursor":null}