{"total":17,"rows":[{"id":"2601.13474","title":"Preconditioning Benefits of Spectral Orthogonalization in Muon","created":"2026-01-20","cited_by_count":30,"area":null},{"id":"2502.09376","title":"LoRA Training Provably Converges to a Low-Rank Global Minimum or It Fails Loudly (But it Probably Won't Fail)","created":"2025-02-13","cited_by_count":20,"area":null},{"id":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20,"area":null},{"id":"2405.17580","title":"Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes","created":"2024-05-27","cited_by_count":18,"area":null},{"id":"2410.18965","title":"On the Crucial Role of Initialization for Matrix Factorization","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2401.11940","title":"Low-Tubal-Rank Tensor Recovery via Factorized Gradient Descent","created":"2024-01-22","cited_by_count":7,"area":null},{"id":"2407.00490","title":"Toward Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixture Models","created":"2024-06-29","cited_by_count":6,"area":null},{"id":"2410.16826","title":"Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2502.00463","title":"Efficient Over-parameterized Matrix Sensing from Noisy Measurements via Alternating Preconditioned Gradient Descent","created":"2025-02-01","cited_by_count":4,"area":null},{"id":"2510.01175","title":"On the Benefits of Weight Normalization for Overparameterized Matrix Sensing","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2602.05887","title":"Escaping Local Minima Provably in Non-convex Matrix Sensing: A Deterministic Framework via Simulated Lifting","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2512.07490","title":"Efficient Low-Tubal-Rank Tensor Estimation via Alternating Preconditioned Gradient Descent","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2602.07479","title":"ODELoRA: Training Low-Rank Adaptation by Solving Ordinary Differential Equations","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2605.00473","title":"Near-optimal and Efficient First-Order Algorithm for Multi-Task Learning with Shared Linear Representation","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2606.31390","title":"Direction-Magnitude Decomposition for Low-Rank Matrix Optimization: Faster Convergence and Saddle-to-saddle Dynamics","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.01947","title":"Divisive Normalization Shapes Low-Rank Slow Manifolds for Continuous Working Memory","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.11479","title":"Convergence Guarantees of Gradient Descent for Neural Networks via Generalized Lipschitz Smoothness","created":"2026-08-11","cited_by_count":0,"area":null}],"next_cursor":null}