{"total":20,"rows":[{"id":"2402.02347","title":"Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models","created":"2024-02-04","cited_by_count":52,"area":null},{"id":"2302.01186","title":"The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing","created":"2023-02-02","cited_by_count":33,"area":null},{"id":"2601.13474","title":"Preconditioning Benefits of Spectral Orthogonalization in Muon","created":"2026-01-20","cited_by_count":30,"area":null},{"id":"2302.10034","title":"Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron","created":"2023-02-20","cited_by_count":25,"area":null},{"id":"2310.01769","title":"How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization","created":"2023-10-03","cited_by_count":18,"area":null},{"id":"2207.01789","title":"Improved Global Guarantees for the Nonconvex Burer--Monteiro Factorization via Rank Overparameterization","created":"2022-07-05","cited_by_count":13,"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":"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":"2602.06880","title":"Decoupling Variance and Scale-Invariant Updates in Adaptive Gradient Descent for Unified Vector and Matrix Optimization","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2410.09640","title":"Provable Acceleration of Nesterov's Accelerated Gradient for Rectangular Matrix Factorization and Linear Neural Networks","created":"2024-10-12","cited_by_count":3,"area":null},{"id":"2506.13710","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2302.10963","title":"Can Learning Be Explained By Local Optimality In Robust Low-rank Matrix Recovery?","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2509.19977","title":"Faster Than SVD, Smarter Than SGD: The OPLoRA Alternating Update","created":"2025-09-24","cited_by_count":1,"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":"2607.13246","title":"Reassessing Muon for Matrix Factorization","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2502.00320","title":"$k$-SVD with Gradient Descent","created":"2025-02-01","cited_by_count":0,"area":null},{"id":"2602.16456","title":"Beyond SGD, Without SVD: Proximal Subspace Iteration LoRA with Diagonal Fractional K-FAC","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.21062","title":"Gradient Descent with Projection Finds Over-Parameterized Neural Networks for Learning Low-Degree Polynomials with Nearly Minimax Optimal Rate","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2604.00060","title":"Scaled Gradient Descent for Ill-Conditioned Low-Rank Matrix Recovery with Optimal Sampling Complexity","created":"2026-03-31","cited_by_count":0,"area":null}],"next_cursor":null}