{"total":13,"rows":[{"id":"2506.04192","title":"Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise","created":"2025-06-04","cited_by_count":41,"area":null},{"id":"2406.01959","title":"Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions","created":"2024-06-04","cited_by_count":6,"area":null},{"id":"2507.12091","title":"Better Convergence Guarantees for Sign-Based Momentum Methods","created":"2025-07-16","cited_by_count":6,"area":null},{"id":"2508.12327","title":"Convergence Analysis of the Lion Optimizer in Centralized and Distributed Settings","created":"2025-08-17","cited_by_count":6,"area":null},{"id":"2604.15416","title":"StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models","created":"2026-04-16","cited_by_count":5,"area":null},{"id":"2410.14054","title":"Adaptive Gradient Normalization and Independent Sampling for (Stochastic) Generalized-Smooth Optimization","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2410.16871","title":"Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2507.08963","title":"Stochastic Approximation with Block Coordinate Optimal Stepsizes","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2605.06615","title":"When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\\ell_1$-norm Lower Bounds","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2604.09276","title":"Distributed Online Convex Optimization with Compressed Communication: Optimal Regret and Applications","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2502.06728","title":"DeToNATION: Decoupled Torch Network-Aware Training on Interlinked Online Nodes","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2602.02355","title":"Mitigating Heterogeneity-Induced Drift in Hierarchical Sign-Based Federated Learning","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2609.18656","title":"Revisiting Distributed Sign-Based Variance Reduction","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}