{"total":47,"rows":[{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192,"area":null},{"id":"2506.15054","title":"Muon Optimizes Under Spectral Norm Constraints","created":"2025-06-18","cited_by_count":86,"area":null},{"id":"2404.04454","title":"Implicit Bias of AdamW: $\\ell_\\infty$ Norm Constrained Optimization","created":"2024-04-05","cited_by_count":58,"area":null},{"id":"2411.16085","title":"Cautious Optimizers: Improving Training with One Line of Code","created":"2024-11-25","cited_by_count":47,"area":null},{"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":"2408.12857","title":"Memory-Efficient LLM Training with Online Subspace Descent","created":"2024-08-23","cited_by_count":39,"area":null},{"id":"2406.10650","title":"The Implicit Bias of Adam on Separable Data","created":"2024-06-15","cited_by_count":36,"area":null},{"id":"2507.01598","title":"Convergence Bound and Critical Batch Size of Muon Optimizer","created":"2025-07-02","cited_by_count":28,"area":null},{"id":"2404.00438","title":"Communication Efficient Distributed Training with Distributed Lion","created":"2024-03-30","cited_by_count":18,"area":null},{"id":"2506.01913","title":"Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness","created":"2025-06-02","cited_by_count":17,"area":null},{"id":"2510.12402","title":"Cautious Weight Decay","created":"2025-10-14","cited_by_count":13,"area":null},{"id":"2603.09952","title":"On the Width Scaling of Neural Optimizers Under Matrix Operator Norms I: Row/Column Normalization and Hyperparameter Transfer","created":"2026-03-10","cited_by_count":12,"area":null},{"id":"2406.09958","title":"Memory-Efficient Optimization with Factorized Hamiltonian Descent","created":"2024-06-14","cited_by_count":11,"area":null},{"id":"2411.07724","title":"Convergence Rate Analysis of LION","created":"2024-11-12","cited_by_count":11,"area":null},{"id":"2411.19870","title":"DeMo: Decoupled Momentum Optimization","created":"2024-11-29","cited_by_count":11,"area":null},{"id":"2511.11466","title":"Non-Euclidean SGD for Structured Optimization: Unified Analysis and Improved Rates","created":"2025-11-14","cited_by_count":8,"area":null},{"id":"2502.02132","title":"How Memory in Optimization Algorithms Implicitly Modifies the Loss","created":"2025-02-04","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":"2605.10797","title":"Muown: Row-Norm Control for Muon Optimization","created":"2026-05-11","cited_by_count":6,"area":null},{"id":"2411.05746","title":"Continuous-Time Analysis of Adaptive Optimization and Normalization","created":"2024-11-08","cited_by_count":4,"area":null},{"id":"2507.05966","title":"Simple Convergence Proof of Adam From a Sign-like Descent Perspective","created":"2025-07-08","cited_by_count":4,"area":null},{"id":"2602.06880","title":"Decoupling Variance and Scale-Invariant Updates in Adaptive Gradient Descent for Unified Vector and Matrix Optimization","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2506.06606","title":"Stacey: Promoting Stochastic Steepest Descent via Accelerated $\\ell_p$-Smooth Nonconvex Optimization","created":"2025-06-07","cited_by_count":3,"area":null},{"id":"2602.01105","title":"OLion: Approaching the Hadamard Ideal by Intersecting Spectral and $\\ell_{\\infty}$ Implicit Biases","created":"2026-02-01","cited_by_count":3,"area":null},{"id":"2602.20360","title":"Momentum Guidance: Plug-and-Play Guidance for Flow Models","created":"2026-02-23","cited_by_count":3,"area":null},{"id":"2605.11172","title":"Optimistic Dual Averaging Unifies Modern Optimizers","created":"2026-05-11","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":"2605.18528","title":"Tight Complexity of Muon under Heavy-Tailed Noise","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2605.19811","title":"LionMuon: Alternating Spectral and Sign Descent for Efficient Training","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2605.26977","title":"Convergence of Spectral Descent for Non-smooth Optimization","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2411.17866","title":"Distributed Sign Momentum with Local Steps for Training Transformers","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2505.01744","title":"Memory-Efficient LLM Training by Various-Grained Low-Rank Projection of Gradients","created":"2025-05-03","cited_by_count":1,"area":null},{"id":"2507.06464","title":"SoftSignSGD(S3): An Enhanced Optimizer for Practical DNN Training and Loss Spikes Minimization Beyond Adam","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2605.04418","title":"Demystifying Manifold Constraints in LLM Pre-training","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2609.17629","title":"Fenchel-Young Duality Gaps: Certified Early Stopping for Regularized Inverse Problems","created":"2026-09-15","cited_by_count":1,"area":null},{"id":"2410.05871","title":"A second-order-like optimizer with adaptive gradient scaling for deep learning","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2512.24445","title":"Adaptive Learning Guided by Bias-Noise-Alignment Diagnostics","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2603.10485","title":"Dual Space Preconditioning for Gradient Descent in the Overparameterized Regime","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.14587","title":"CLion: Efficient Cautious Lion Optimizer with Enhanced Generalization","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.05577","title":"Accelerating LMO-Based Optimization via Implicit Gradient Transport","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.06868","title":"When Descent Is Too Stable: Event-Triggered Hamiltonian Learning to Optimize","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.09991","title":"Optimizer-Induced Mode Connectivity: From AdamW to Muon","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.11850","title":"Constrained Stochastic Spectral Preconditioning Converges for Nonconvex Objectives","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.02078","title":"Beyond $\\ell_2$-norm and $\\ell_\\infty$-norm: A Curvature-Inspired $\\ell_p$-Norm Scheme for Deep Neural Networks","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.31591","title":"Evil Spectra: How Optimisers can Amplify or Suppress Emergent Misalignment","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.35297","title":"LionMuon: Alternating Spectral and Sign Descent for Efficient Training","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.10975","title":"Optimizing Large Language Models with Chained LMOs","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}