{"total":36,"rows":[{"id":"2506.15054","title":"Muon Optimizes Under Spectral Norm Constraints","created":"2025-06-18","cited_by_count":86,"area":null},{"id":"2412.05270","title":"APOLLO: SGD-like Memory, AdamW-level Performance","created":"2024-12-06","cited_by_count":54,"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":"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":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20,"area":null},{"id":"2502.01586","title":"SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training","created":"2025-02-03","cited_by_count":16,"area":null},{"id":"2504.20437","title":"GaLore 2: Large-Scale LLM Pre-Training by Gradient Low-Rank Projection","created":"2025-04-29","cited_by_count":14,"area":null},{"id":"2510.12402","title":"Cautious Weight Decay","created":"2025-10-14","cited_by_count":13,"area":null},{"id":"2602.17155","title":"Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization","created":"2026-02-19","cited_by_count":12,"area":null},{"id":"2411.19870","title":"DeMo: Decoupled Momentum Optimization","created":"2024-11-29","cited_by_count":11,"area":null},{"id":"2507.08784","title":"Greedy Low-Rank Gradient Compression for Distributed Learning with Convergence Guarantees","created":"2025-07-11","cited_by_count":11,"area":null},{"id":"2506.08001","title":"Reparameterized LLM Training via Orthogonal Equivalence Transformation","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2502.05790","title":"Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining","created":"2025-02-09","cited_by_count":7,"area":null},{"id":"2509.18993","title":"CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure","created":"2025-09-23","cited_by_count":7,"area":null},{"id":"2505.22922","title":"Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2603.05500","title":"POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2509.05213","title":"An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data","created":"2025-09-05","cited_by_count":4,"area":null},{"id":"2601.21929","title":"LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution","created":"2026-01-29","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":"2411.07120","title":"Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2505.17967","title":"FFT-based Dynamic Subspace Selection for Low-Rank Adaptive Optimization of Large Language Models","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2509.23472","title":"Memory-Efficient Fine-Tuning via Low-Rank Activation Compression","created":"2025-09-27","cited_by_count":2,"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":"2510.01878","title":"Geometrically Principled Randomized Optimization for Efficient LLM Training","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2602.23111","title":"PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2604.09406","title":"OASIS: Online Activation Subspace Learning for Memory-Efficient Training","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2605.06316","title":"Pro-KLShampoo: Projected KL-Shampoo with Whitening Recovered by Orthogonalization","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2505.18313","title":"PLUMAGE: Probabilistic Low rank Unbiased Min Variance Gradient Estimator for Efficient Large Model Training","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2602.01233","title":"Lotus: Efficient LLM Training by Randomized Low-Rank Gradient Projection with Adaptive Subspace Switching","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.08007","title":"From $O(mn)$ to $O(r^2)$: Two-Sided Low-Rank Communication for Adam in Distributed Training with Memory Efficiency","created":"2026-02-08","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":"2609.15037","title":"MoARa: Module-Aware Rank Allocation and Structure-Preserving Decomposition for Low-Rank LLM Pre-training","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.35257","title":"AIM-ZO: Activation-Informed Subspace Maintenance for Zeroth-Order LLM Fine-Tuning","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04204","title":"Clean: Second-order LLM Training at Linear Memory Cost via Nystr{\\\"o}m Sketching","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.19844","title":"Memory-Efficient Subspace Optimization with Residual Correction: From Momentum SGD to Muon","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}