{"total":59,"rows":[{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134,"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":"2206.03665","title":"Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression","created":"2022-06-08","cited_by_count":33,"area":null},{"id":"2302.07173","title":"An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learning","created":"2023-02-14","cited_by_count":32,"area":null},{"id":"2102.01583","title":"The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication","created":"2021-02-02","cited_by_count":31,"area":null},{"id":"2110.01463","title":"Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits","created":"2021-10-04","cited_by_count":31,"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":"2102.04635","title":"Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity","created":"2021-02-09","cited_by_count":21,"area":null},{"id":"2204.13169","title":"FedShuffle: Recipes for Better Use of Local Work in Federated Learning","created":"2022-04-27","cited_by_count":21,"area":null},{"id":"2204.09837","title":"Memory Bounds for the Experts Problem","created":"2022-04-21","cited_by_count":20,"area":null},{"id":"2106.04759","title":"Communication-efficient SGD: From Local SGD to One-Shot Averaging","created":"2021-06-09","cited_by_count":19,"area":null},{"id":"2209.02257","title":"Faster federated optimization under second-order similarity","created":"2022-09-06","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":"2203.15260","title":"Efficient Convex Optimization Requires Superlinear Memory","created":"2022-03-29","cited_by_count":14,"area":null},{"id":"2302.03662","title":"Federated Learning with Regularized Client Participation","created":"2023-02-07","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":"2202.01087","title":"Communication Efficient Federated Learning for Generalized Linear Bandits","created":"2022-02-02","cited_by_count":13,"area":null},{"id":"2108.06869","title":"FedChain: Chained Algorithms for Near-Optimal Communication Cost in Federated Learning","created":"2021-08-16","cited_by_count":11,"area":null},{"id":"2304.07504","title":"Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis","created":"2023-04-15","cited_by_count":11,"area":null},{"id":"2305.07612","title":"Lower Bounds and Accelerated Algorithms in Distributed Stochastic Optimization with Communication Compression","created":"2023-05-12","cited_by_count":11,"area":null},{"id":"2205.15136","title":"Optimal Gradient Sliding and its Application to Distributed Optimization Under Similarity","created":"2022-05-30","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":"2206.09446","title":"Compression and Data Similarity: Combination of Two Techniques for Communication-Efficient Solving of Distributed Variational Inequalities","created":"2022-06-19","cited_by_count":8,"area":null},{"id":"2302.03542","title":"Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy","created":"2023-02-07","cited_by_count":7,"area":null},{"id":"2302.07615","title":"Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities","created":"2023-02-15","cited_by_count":7,"area":null},{"id":"2302.04963","title":"Quadratic Memory is Necessary for Optimal Query Complexity in Convex Optimization: Center-of-Mass is Pareto-Optimal","created":"2023-02-09","cited_by_count":5,"area":null},{"id":"2206.09576","title":"FedSSO: A Federated Server-Side Second-Order Optimization Algorithm","created":"2022-06-20","cited_by_count":3,"area":null},{"id":"2101.01505","title":"Delayed Projection Techniques for Linearly Constrained Problems: Convergence Rates, Acceleration, and Applications","created":"2021-01-05","cited_by_count":2,"area":null},{"id":"2105.14216","title":"CDMA: A Practical Cross-Device Federated Learning Algorithm for General Minimax Problems","created":"2021-05-29","cited_by_count":2,"area":null},{"id":"2110.05178","title":"Gradual Federated Learning with Simulated Annealing","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2210.03521","title":"STSyn: Speeding Up Local SGD with Straggler-Tolerant Synchronization","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2305.10294","title":"DualFL: A Duality-based Federated Learning Algorithm with Communication Acceleration in the General Convex Regime","created":"2023-05-17","cited_by_count":2,"area":null},{"id":"2409.14280","title":"Accelerated Stochastic ExtraGradient: Mixing Hessian and Gradient Similarity to Reduce Communication in Distributed and Federated Learning","created":"2024-09-22","cited_by_count":2,"area":null},{"id":"2412.16414","title":"Accelerated Methods with Compressed Communications for Distributed Optimization Problems under Data Similarity","created":"2024-12-21","cited_by_count":2,"area":null},{"id":"2506.13974","title":"Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2511.13999","title":"On the Gradient Complexity of Private Optimization with Private Oracles","created":"2025-11-17","cited_by_count":2,"area":null},{"id":"2205.10247","title":"SADAM: Stochastic Adam, A Stochastic Operator for First-Order Gradient-based Optimizer","created":"2022-05-20","cited_by_count":1,"area":null},{"id":"2306.10395","title":"Distributed Semi-Supervised Sparse Statistical Inference","created":"2023-06-17","cited_by_count":1,"area":null},{"id":"2401.07809","title":"Optimal Data Splitting in Distributed Optimization for Machine Learning","created":"2024-01-15","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":"2406.00846","title":"Local Methods with Adaptivity via Scaling","created":"2024-06-02","cited_by_count":1,"area":null},{"id":"2412.17082","title":"MARINA-P: Superior Performance in Non-smooth Federated Optimization with Adaptive Stepsizes","created":"2024-12-22","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":"2512.05327","title":"Non-Convex Federated Optimization under Cost-Aware Client Selection","created":"2025-12-05","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":"2606.00703","title":"Information-Theoretic Lower Bounds for Bit-Constrained Stochastic Optimization via a Reduction to Compressed Gaussian Mean Estimation","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2208.03249","title":"Parameter Averaging for Feature Ranking","created":"2022-08-05","cited_by_count":0,"area":null},{"id":"2405.16126","title":"Near-Optimal Distributed Minimax Optimization under the Second-Order Similarity","created":"2024-05-25","cited_by_count":0,"area":null},{"id":"2412.01389","title":"Refined Analysis of Federated Averaging and Federated Richardson-Romberg","created":"2024-12-02","cited_by_count":0,"area":null},{"id":"2505.11748","title":"HOME-3: High-Order Momentum Estimator with Third-Power Gradient for Convex and Smooth Nonconvex Optimization","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2505.11752","title":"Permutation Randomization on Nonsmooth Nonconvex Optimization: A Theoretical and Experimental Study","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2506.15387","title":"Multi-Timescale Primal Dual Hybrid Gradient with Application to Distributed Optimization","created":"2025-06-18","cited_by_count":0,"area":null},{"id":"2507.11183","title":"Quantized Rank Reduction: A Communications-Efficient Federated Learning Scheme for Network-Critical Applications","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2509.02538","title":"Federated learning over physical channels: adaptive algorithms with near-optimal guarantees","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2601.08614","title":"Accelerated Methods with Complexity Separation Under Data Similarity for Federated Learning Problems","created":"2026-01-13","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":"2607.24827","title":"Stronger Memory-Query Tradeoffs for Convex Optimization: The Limitations of Subquadratic Memory","created":"2026-07-21","cited_by_count":0,"area":null}],"next_cursor":null}