{"total":25,"rows":[{"id":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2405.16002","title":"Does SGD really happen in tiny subspaces?","created":"2024-05-25","cited_by_count":36,"area":null},{"id":"2405.18199","title":"Adam with model exponential moving average is effective for nonconvex optimization","created":"2024-05-28","cited_by_count":23,"area":null},{"id":"2405.09742","title":"Random Scaling and Momentum for Non-smooth Non-convex Optimization","created":"2024-05-16","cited_by_count":19,"area":null},{"id":"2411.07061","title":"General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization","created":"2024-11-11","cited_by_count":15,"area":null},{"id":"2402.02720","title":"Discounted Adaptive Online Learning: Towards Better Regularization","created":"2024-02-05","cited_by_count":12,"area":null},{"id":"2502.16484","title":"A Fine-Tuning Approach for T5 Using Knowledge Graphs to Address Complex Tasks","created":"2025-02-23","cited_by_count":6,"area":null},{"id":"2505.22899","title":"On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning","created":"2025-05-28","cited_by_count":5,"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":"2608.26288","title":"Muon with Finite Newton-Schulz: The Smoothing Benefit in Nonsmooth Nonconvex Optimization","created":"2026-08-26","cited_by_count":5,"area":null},{"id":"2602.08372","title":"Dynamic Regret via Discounted-to-Dynamic Reduction with Applications to Curved Losses and Adam Optimizer","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2407.01825","title":"Reevaluating Theoretical Analysis Methods for Optimization in Deep Learning","created":"2024-07-01","cited_by_count":3,"area":null},{"id":"2510.03167","title":"Improving Online-to-Nonconvex Conversion for Smooth Optimization via Double Optimism","created":"2025-10-03","cited_by_count":3,"area":null},{"id":"2505.19491","title":"Discounted Online Convex Optimization: Uniform Regret Across a Continuous Interval","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2510.03478","title":"How to Set $\\beta_1, \\beta_2$ in Adam: An Online Learning Perspective","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2606.02365","title":"FOAM: Frequency and Operator Error-Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2607.27383","title":"The Convergence Behavior of Adam under Heavy-Tailed Noise","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2607.03519","title":"On the Convergence of Adam, Revisited","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2608.19762","title":"Finite-Horizon Input-Output Dynamics of Minibatch Perturbations in AdamW","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2605.15522","title":"Stochastic Non-Smooth Convex Optimization with Unbounded Gradients","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.01325","title":"SEArch: Optimistic Policy Selection Between Scene Noise and Drift for UAV Radar Search","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.22326","title":"Adam Converges in Nonsmooth Nonconvex Optimization","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2607.17607","title":"Optimizing the Preconditioner: A Black-box Online-to-Nonconvex Conversion with Static Regret Minimization Oracles","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2610.08624","title":"Early Memory Selection for Balanced Adam","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.13787","title":"Optimal Algorithms for Nonsmooth Nonconvex Stochastic Optimization with Constraints","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}