{"total":45,"rows":[{"id":"2110.03677","title":"Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect","created":"2021-10-07","cited_by_count":50,"area":null},{"id":"2305.00316","title":"The Ideal Continual Learner: An Agent That Never Forgets","created":"2023-04-29","cited_by_count":35,"area":null},{"id":"2203.02839","title":"Algorithmic Regularization in Model-free Overparametrized Asymmetric Matrix Factorization","created":"2022-03-06","cited_by_count":34,"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":"2203.03756","title":"Flat minima generalize for low-rank matrix recovery","created":"2022-03-07","cited_by_count":28,"area":null},{"id":"2310.11028","title":"Matrix Compression via Randomized Low Rank and Low Precision Factorization","created":"2023-10-17","cited_by_count":25,"area":null},{"id":"2310.17087","title":"Good regularity creates large learning rate implicit biases: edge of stability, balancing, and catapult","created":"2023-10-26","cited_by_count":25,"area":null},{"id":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20,"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":"2410.18965","title":"On the Crucial Role of Initialization for Matrix Factorization","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2305.06927","title":"Convergence of Alternating Gradient Descent for Matrix Factorization","created":"2023-05-11","cited_by_count":12,"area":null},{"id":"2203.14383","title":"Continual learning: a feature extraction formalization, an efficient algorithm, and fundamental obstructions","created":"2022-03-27","cited_by_count":11,"area":null},{"id":"2204.11516","title":"Randomly Initialized Alternating Least Squares: Fast Convergence for Matrix Sensing","created":"2022-04-25","cited_by_count":11,"area":null},{"id":"2303.15256","title":"Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need","created":"2023-03-27","cited_by_count":9,"area":null},{"id":"2308.14929","title":"Maestro: Uncovering Low-Rank Structures via Trainable Decomposition","created":"2023-08-28","cited_by_count":8,"area":null},{"id":"2212.04025","title":"A Novel Stochastic Gradient Descent Algorithm for Learning Principal Subspaces","created":"2022-12-08","cited_by_count":7,"area":null},{"id":"2406.04596","title":"Federated Representation Learning in the Under-Parameterized Regime","created":"2024-06-07","cited_by_count":7,"area":null},{"id":"2509.25351","title":"Gradient Descent with Large Step Sizes: Chaos and Fractal Convergence Region","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2111.08706","title":"How and When Random Feedback Works: A Case Study of Low-Rank Matrix Factorization","created":"2021-11-17","cited_by_count":5,"area":null},{"id":"2204.14067","title":"Accelerating nuclear-norm regularized low-rank matrix optimization through Burer-Monteiro decomposition","created":"2022-04-29","cited_by_count":5,"area":null},{"id":"2108.01772","title":"Nonconvex Factorization and Manifold Formulations are Almost Equivalent in Low-rank Matrix Optimization","created":"2021-08-03","cited_by_count":4,"area":null},{"id":"2209.15130","title":"Nonconvex Matrix Factorization is Geodesically Convex: Global Landscape Analysis for Fixed-rank Matrix Optimization From a Riemannian Perspective","created":"2022-09-29","cited_by_count":4,"area":null},{"id":"2210.00346","title":"Behind the Scenes of Gradient Descent: A Trajectory Analysis via Basis Function Decomposition","created":"2022-10-01","cited_by_count":4,"area":null},{"id":"2212.09396","title":"Rank-1 Matrix Completion with Gradient Descent and Small Random Initialization","created":"2022-12-19","cited_by_count":4,"area":null},{"id":"2402.18905","title":"Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion","created":"2024-02-29","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":"2410.21262","title":"BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference","created":"2024-10-28","cited_by_count":3,"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":"2604.21905","title":"Low-Rank Adaptation Redux for Large Models","created":"2026-04-23","cited_by_count":3,"area":null},{"id":"2605.31484","title":"Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2309.01796","title":"Implicit Regularization Makes Overparameterized Asymmetric Matrix Sensing Robust to Perturbations","created":"2023-09-04","cited_by_count":2,"area":null},{"id":"2409.08771","title":"In-depth Analysis of Low-rank Matrix Factorisation in a Federated Setting","created":"2024-09-13","cited_by_count":2,"area":null},{"id":"2303.11453","title":"Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing","created":"2023-03-20","cited_by_count":1,"area":null},{"id":"2406.02431","title":"Reweighted Solutions for Weighted Low Rank Approximation","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2410.20119","title":"On Multi-Stage Loss Dynamics in Neural Networks: Mechanisms of Plateau and Descent Stages","created":"2024-10-26","cited_by_count":1,"area":null},{"id":"2502.07739","title":"HRP: High-Rank Preheating for Superior LoRA Initialization","created":"2025-02-11","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":"2303.14244","title":"Implicit Balancing and Regularization: Generalization and Convergence Guarantees for Overparameterized Asymmetric Matrix Sensing","created":"2023-03-24","cited_by_count":0,"area":null},{"id":"2410.05022","title":"On subdifferential chain rule of matrix factorization and beyond","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2411.15972","title":"Stability properties of gradient flow dynamics for the symmetric low-rank matrix factorization problem","created":"2024-11-24","cited_by_count":0,"area":null},{"id":"2508.09685","title":"Global Convergence Analysis of Vanilla Gradient Descent for Asymmetric Matrix Completion","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2508.15141","title":"Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2510.22667","title":"Block Coordinate Descent for Neural Networks Provably Finds Global Minima","created":"2025-10-26","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":"2610.09356","title":"Global Exponential Convergence of Two-Layer Linear Network Training","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}