{"total":18,"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":"2508.04860","title":"Can SGD Handle Heavy-Tailed Noise?","created":"2025-08-06","cited_by_count":17,"area":null},{"id":"2602.17080","title":"Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum","created":"2026-02-19","cited_by_count":14,"area":null},{"id":"2603.14315","title":"Enhancing LLM Training via Spectral Clipping","created":"2026-03-15","cited_by_count":10,"area":null},{"id":"2605.06884","title":"Muon with Nesterov Momentum: Heavy-Tailed Noise and (Randomized) Inexact Polar Decomposition","created":"2026-05-07","cited_by_count":8,"area":null},{"id":"2502.13482","title":"Smoothed Normalization for Efficient Distributed Private Optimization","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2605.18694","title":"Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2605.11838","title":"Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.18528","title":"Tight Complexity of Muon under Heavy-Tailed Noise","created":"2026-05-18","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":"2606.23676","title":"Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2607.08104","title":"Vanilla SGD with Momentum Survives Heavy-Tailed Noise: Convergence Analysis without Gradient Clipping or Normalization","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2507.13283","title":"Stochastic Weakly Convex Optimization Under Heavy-Tailed Noises","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2512.05790","title":"Learnability Window in Gated Recurrent Neural Networks","created":"2025-12-05","cited_by_count":0,"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":"2609.12785","title":"Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise and H\\\"{o}lder Smoothness","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.30276","title":"Why Clipping Matters in AdaGrad? Toward a High-Probability Theory under Generalized Smoothness","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.32729","title":"Revisiting AdaGrad in Stochastic Convex Optimization: Last Iterates, High Probability, and Lower Bounds","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}