{"total":19,"rows":[{"id":"2509.14562","title":"LiMuon: Light and Fast Muon Optimizer for Large Models","created":"2025-09-18","cited_by_count":22,"area":null},{"id":"2603.09697","title":"Mousse: Rectifying the Geometry of Muon with Curvature-Aware Preconditioning","created":"2026-03-10","cited_by_count":17,"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":"2509.11259","title":"ICR-RL: Deep Reinforcement Learning via In-Context Regression","created":"2025-09-14","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":"2511.06961","title":"Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings","created":"2025-11-10","cited_by_count":5,"area":null},{"id":"2601.22137","title":"PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network Training","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2604.12968","title":"Evolution of Optimization Methods: Algorithms, Scenarios, and Evaluations","created":"2026-04-14","cited_by_count":3,"area":null},{"id":"2605.19619","title":"MiMuon: Mixed Muon Optimizer with Improved Generalization for Large Models","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2602.09169","title":"Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2509.15113","title":"Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2509.21296","title":"No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2608.05088","title":"MALT: Lightweight Curvature-Aware Muon via Diagonal Preconditioning","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.25990","title":"Spectral Allocation: Why Muon Outperforms Adam, and How to Improve Muon","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2603.08914","title":"Uncovering a Winning Lottery Ticket with Continuously Relaxed Bernoulli Gates","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2607.05872","title":"No Subspace to Track: Non-Identifiability and Optimizer State in Low-Rank Training","created":"2026-07-07","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":"2610.18294","title":"Which Optimizer Leaks Most? Optimizer Implicit Bias as a Training-Data Privacy Controller","created":"2026-10-13","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}