{"total":52,"rows":[{"id":"2409.20325","title":"Old Optimizer, New Norm: An Anthology","created":"2024-09-30","cited_by_count":193,"area":null},{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192,"area":null},{"id":"2405.15682","title":"The Road Less Scheduled","created":"2024-05-24","cited_by_count":163,"area":null},{"id":"2510.05491","title":"NorMuon: Making Muon more efficient and scalable","created":"2025-10-07","cited_by_count":84,"area":null},{"id":"2410.21265","title":"Modular Duality in Deep Learning","created":"2024-10-28","cited_by_count":77,"area":null},{"id":"2311.00636","title":"Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures","created":"2023-11-01","cited_by_count":49,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"area":null},{"id":"2502.04664","title":"Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data","created":"2025-02-07","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":"2502.17410","title":"COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs","created":"2025-02-24","cited_by_count":30,"area":null},{"id":"2402.02887","title":"Time-, Memory- and Parameter-Efficient Visual Adaptation","created":"2024-02-05","cited_by_count":28,"area":null},{"id":"2506.03595","title":"Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner","created":"2025-06-04","cited_by_count":23,"area":null},{"id":"2405.02200","title":"Position: Why We Must Rethink Empirical Research in Machine Learning","created":"2024-05-03","cited_by_count":19,"area":null},{"id":"2411.14708","title":"Understanding LLM Embeddings for Regression","created":"2024-11-22","cited_by_count":19,"area":null},{"id":"2509.03378","title":"Understanding and Improving Shampoo and SOAP via Kullback-Leibler Minimization","created":"2025-09-03","cited_by_count":16,"area":null},{"id":"2510.25000","title":"What Really Matters in Matrix-Whitening Optimizers?","created":"2025-10-28","cited_by_count":16,"area":null},{"id":"2308.07832","title":"REFORMS: Reporting Standards for Machine Learning Based Science","created":"2023-08-15","cited_by_count":13,"area":null},{"id":"2406.04558","title":"On PI Controllers for Updating Lagrange Multipliers in Constrained Optimization","created":"2024-06-07","cited_by_count":12,"area":null},{"id":"2605.18106","title":"Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers","created":"2026-05-18","cited_by_count":11,"area":"moe"},{"id":"2602.03702","title":"Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging","created":"2026-02-03","cited_by_count":10,"area":null},{"id":"2506.04430","title":"Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order","created":"2025-06-04","cited_by_count":9,"area":null},{"id":"2507.09846","title":"Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training","created":"2025-07-14","cited_by_count":9,"area":null},{"id":"2605.08980","title":"Muon Does Not Converge on Convex Lipschitz Functions","created":"2026-05-09","cited_by_count":9,"area":null},{"id":"2401.07250","title":"Stabilizing Sharpness-aware Minimization Through A Simple Renormalization Strategy","created":"2024-01-14","cited_by_count":8,"area":null},{"id":"2402.16565","title":"Partial Rankings of Optimizers","created":"2024-02-26","cited_by_count":8,"area":null},{"id":"2410.12455","title":"Loss Landscape Characterization of Neural Networks without Over-Parametrization","created":"2024-10-16","cited_by_count":8,"area":null},{"id":"2509.26337","title":"FedMuon: Federated Learning with Bias-corrected LMO-based Optimization","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2510.19376","title":"Optimization Benchmark for Diffusion Models on Dynamical Systems","created":"2025-10-22","cited_by_count":7,"area":"diffusion"},{"id":"2402.02342","title":"MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters","created":"2024-02-04","cited_by_count":5,"area":null},{"id":"2501.12670","title":"Celo: Training Versatile Learned Optimizers on a Compute Diet","created":"2025-01-22","cited_by_count":4,"area":null},{"id":"2605.22432","title":"AMUSE: Anytime Muon with Stable Gradient Evaluation","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2411.03493","title":"LASER: Attention with Exponential Transformation","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2505.24005","title":"How far away are truly hyperparameter-free learning algorithms?","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2510.00236","title":"Per-example gradients: a new frontier for understanding and improving optimizers","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2602.02016","title":"DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers","created":"2026-02-02","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":"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":"2505.13397","title":"Learning by solving differential equations","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2511.06477","title":"DyKAF: Dynamical Kronecker Approximation of the Fisher Information Matrix for Gradient Preconditioning","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2602.19142","title":"Celo2: Towards Learned Optimization Free Lunch","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2606.14259","title":"Beyond a Single Explanation of the Adam--SGD Gap","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2405.00156","title":"Expanding the Horizon: Enabling Hybrid Quantum Transfer Learning for Long-Tailed Chest X-Ray Classification","created":"2024-04-30","cited_by_count":0,"area":null},{"id":"2406.18701","title":"Fast Optimizer Benchmark","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2607.09167","title":"Understanding Schedule-Free Methods in Nonconvex Optimization: Rate Guarantees and Escaping Saddles","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.05136","title":"The Loss Does Not See the Basis, but Adam Does","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.11867","title":"AdamX: Cosine similarity meets gradient descent","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.13922","title":"Minibatch persistency, eight years later: what batch reuse costs in steps and joules, and what it saves in data","created":"2026-09-12","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":"2610.08534","title":"How Bregman Divergences Shape Shampoo","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.08975","title":"The Best Optimizer Depends on Batch Size","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.09425","title":"What a Reporting Convention Hides: A Matched-Budget Audit of Quantum Natural Gradient with an Exactly Computed Metric","created":"2026-10-07","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}],"next_cursor":null}