{"total":39,"rows":[{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337,"area":null},{"id":"2304.00488","title":"Saddle-to-Saddle Dynamics in Diagonal Linear Networks","created":"2023-04-02","cited_by_count":57,"area":null},{"id":"2306.07042","title":"Transformers learn through gradual rank increase","created":"2023-06-12","cited_by_count":52,"area":null},{"id":"2402.11867","title":"LoRA Training in the NTK Regime has No Spurious Local Minima","created":"2024-02-19","cited_by_count":48,"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":"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":"2306.06479","title":"Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs","created":"2023-06-10","cited_by_count":16,"area":null},{"id":"2508.12837","title":"Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points","created":"2025-08-18","cited_by_count":16,"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":"2503.06982","title":"Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization","created":"2025-03-10","cited_by_count":13,"area":null},{"id":"2402.09226","title":"Directional Convergence Near Small Initializations and Saddles in Two-Homogeneous Neural Networks","created":"2024-02-14","cited_by_count":11,"area":null},{"id":"2409.09745","title":"The Optimality of (Accelerated) SGD for High-Dimensional Quadratic Optimization","created":"2024-09-15","cited_by_count":8,"area":null},{"id":"2403.08121","title":"Early Directional Convergence in Deep Homogeneous Neural Networks for Small Initializations","created":"2024-03-12","cited_by_count":7,"area":null},{"id":"2305.17224","title":"Fast and Accurate Estimation of Low-Rank Matrices from Noisy Measurements via Preconditioned Non-Convex Gradient Descent","created":"2023-05-26","cited_by_count":5,"area":null},{"id":"2310.14423","title":"A Quadratic Synchronization Rule for Distributed Deep Learning","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2410.05448","title":"Task Diversity Shortens the ICL Plateau","created":"2024-10-07","cited_by_count":5,"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":"2311.05061","title":"Efficient Compression of Overparameterized Deep Models through Low-Dimensional Learning Dynamics","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2405.13721","title":"Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2408.13276","title":"Non-convex matrix sensing: Breaking the quadratic rank barrier in the sample complexity","created":"2024-08-20","cited_by_count":3,"area":null},{"id":"2505.22602","title":"One Rank at a Time: Cascading Error Dynamics in Sequential Learning","created":"2025-05-28","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":"2305.19206","title":"Gradient descent in matrix factorization: Understanding large initialization","created":"2023-05-30","cited_by_count":2,"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":"2403.01420","title":"The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing","created":"2024-03-03","cited_by_count":2,"area":null},{"id":"2510.21078","title":"Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2602.19143","title":"Incremental Learning of Sparse Attention Patterns in Transformers","created":"2026-02-22","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":"2310.15549","title":"Algorithmic Regularization in Tensor Optimization: Towards a Lifted Approach in Matrix Sensing","created":"2023-10-24","cited_by_count":1,"area":null},{"id":"2403.06056","title":"Absence of spurious solutions far from ground truth: A low-rank analysis with high-order losses","created":"2024-03-10","cited_by_count":1,"area":null},{"id":"2408.13767","title":"Lecture Notes on Linear Neural Networks: A Tale of Optimization and Generalization in Deep Learning","created":"2024-08-25","cited_by_count":1,"area":null},{"id":"2508.20344","title":"Understanding Incremental Learning with Closed-form Solution to Gradient Flow on Overparamerterized Matrix Factorization","created":"2025-08-28","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":"2305.15276","title":"Sparse Mean Estimation in Adversarial Settings via Incremental Learning","created":"2023-05-24","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":"2610.04142","title":"Ideal Paths for Approximating Logistic Gradient Descent Trajectories at Large Initialization","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04249","title":"Optimizer Geometry Sets the Pace: Spectral Learning Dynamics in Matrix Factorization","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}