{"total":64,"rows":[{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428,"area":"moe"},{"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":"2503.20762","title":"ASGO: Adaptive Structured Gradient Optimization","created":"2025-03-26","cited_by_count":57,"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":"2503.10537","title":"Structured Preconditioners in Adaptive Optimization: A Unified Analysis","created":"2025-03-13","cited_by_count":33,"area":null},{"id":"2509.15816","title":"On the Convergence of Muon and Beyond","created":"2025-09-19","cited_by_count":31,"area":null},{"id":"2502.19002","title":"The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training","created":"2025-02-26","cited_by_count":30,"area":null},{"id":"2510.01037","title":"CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs","created":"2025-10-01","cited_by_count":19,"area":"lr"},{"id":"2604.01472","title":"The Newton-Muon Optimizer","created":"2026-04-01","cited_by_count":18,"area":null},{"id":"2603.28254","title":"MuonEq: Balancing Before Orthogonalization with Lightweight Equilibration","created":"2026-03-30","cited_by_count":17,"area":null},{"id":"2510.25000","title":"What Really Matters in Matrix-Whitening Optimizers?","created":"2025-10-28","cited_by_count":16,"area":null},{"id":"2603.20527","title":"RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization","created":"2026-03-20","cited_by_count":15,"area":null},{"id":"2601.23000","title":"Mano: Restriking Manifold Optimization for LLM Training","created":"2026-01-30","cited_by_count":12,"area":null},{"id":"2603.10067","title":"HTMuon: Improving Muon via Heavy-Tailed Spectral Correction","created":"2026-03-10","cited_by_count":12,"area":null},{"id":"2510.21800","title":"MARS-M: When Variance Reduction Meets Matrices","created":"2025-10-20","cited_by_count":10,"area":null},{"id":"2603.14315","title":"Enhancing LLM Training via Spectral Clipping","created":"2026-03-15","cited_by_count":10,"area":null},{"id":"2602.04669","title":"Delving into Muon and Beyond: Deep Analysis and Extensions","created":"2026-02-04","cited_by_count":9,"area":null},{"id":"2501.12243","title":"FOCUS: First Order Concentrated Updating Scheme","created":"2025-01-21","cited_by_count":8,"area":null},{"id":"2501.12391","title":"Physics of Skill Learning","created":"2025-01-21","cited_by_count":8,"area":null},{"id":"2505.24275","title":"GradPower: Powering Gradients for Faster Language Model Pre-Training","created":"2025-05-30","cited_by_count":8,"area":null},{"id":"2602.09314","title":"Clarifying Shampoo: Adapting Spectral Descent to Stochasticity and the Parameter Trajectory","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2602.22681","title":"Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement","created":"2026-02-26","cited_by_count":8,"area":null},{"id":"2502.10563","title":"Accelerating Unbiased LLM Evaluation via Synthetic Feedback","created":"2025-02-14","cited_by_count":7,"area":"alignment"},{"id":"2602.13498","title":"TrasMuon: Trust-Region Adaptive Scaling for Orthogonalized Momentum Optimizers","created":"2026-02-13","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":"2605.06654","title":"Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2604.09258","title":"Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima","created":"2026-04-10","cited_by_count":4,"area":null},{"id":"2510.14009","title":"Noise-Adaptive Layerwise Learning Rates: Accelerating Geometry-Aware Optimization for Deep Neural Network Training","created":"2025-10-15","cited_by_count":3,"area":null},{"id":"2502.08612","title":"Continuous Cardiac Arrest Prediction in ICU using PPG Foundation Model","created":"2025-02-12","cited_by_count":2,"area":null},{"id":"2506.01049","title":"Taming LLMs by Scaling Learning Rates with Gradient Grouping","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2511.14501","title":"Improved Convergence in Parameter-Agnostic Error Feedback through Momentum","created":"2025-11-18","cited_by_count":2,"area":null},{"id":"2512.06370","title":"Greedy Alignment Principle for Optimizer Selection","created":"2025-12-06","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":"2606.17526","title":"MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2507.17501","title":"DNT: a Deeply Normalized Transformer that can be trained by Momentum SGD","created":"2025-07-23","cited_by_count":1,"area":null},{"id":"2509.21695","title":"Wav2Arrest 2.0: Long-Horizon Cardiac Arrest Prediction with Time-to-Event Modeling, Identity-Invariance, and Pseudo-Lab Alignment","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2510.04988","title":"Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2607.14536","title":"Muse: Representation Geometry of Muon Beyond Normalized Momentum","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2607.20486","title":"OPTScientist: Multi-Agent Discovery of Typed Optimizer Programs for Transformer Pretraining","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2601.01306","title":"Towards a Principled Muon under $\\mu\\mathsf{P}$: Ensuring Spectral Conditions throughout Training","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2602.01505","title":"Optimal Sample Complexity for Single Time-Scale Actor-Critic with Momentum","created":"2026-02-02","cited_by_count":0,"area":"deeprl"},{"id":"2603.09923","title":"OptEMA: Adaptive Exponential Moving Average for Stochastic Optimization with Zero-Noise Optimality","created":"2026-03-10","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":"2605.02143","title":"Personalized Federated Learning for Gradient Alignment","created":"2026-05-04","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":"2605.08871","title":"Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction","created":"2026-05-09","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":"2605.17806","title":"AMO: Operator-level Adaptive Muon Orthogonalization","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.30634","title":"One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.04033","title":"OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2608.21024","title":"RODE: A Radial-Orthogonal Decoupled Engine for Optimization","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.28442","title":"Curvature-Conditioned Multiscale Momentum with Sphere Constraints for LLM Pretraining","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.28557","title":"Blog: Survey of Optimizers","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.23055","title":"Optimizers for Diffusion Models: A Controlled Benchmark","created":"2026-09-19","cited_by_count":0,"area":"diffusion"},{"id":"2609.24233","title":"Adaptive Forgetting for Nonstationary Optimization: Towards Robust EEG Decoding","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.34960","title":"ProofLoom: Proof-Obligation-Driven Theory Construction for Autoformalizing Research-Level Stochastic Optimization","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36600","title":"Second-Moment Stochastic Approximation Methods","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37745","title":"Optimizer-dependent training dynamics converge to the same one-third optimal data scaling","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.03432","title":"OptiSelect: How does the Optimizer Shape Data Curriculum?","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.13036","title":"Towards Easier-to-Tune Training Algorithms: New Results from AlgoPerf","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.13789","title":"Randomized Momentum Transport with Cheap Predictors","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16923","title":"Minimax Optimality of Shampoo for Nonstationary Stochastic Optimization","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}