{"total":78,"rows":[{"id":"2206.15144","title":"Neural Networks can Learn Representations with Gradient Descent","created":"2022-06-30","cited_by_count":161,"area":null},{"id":"2111.00034","title":"Neural Networks as Kernel Learners: The Silent Alignment Effect","created":"2021-10-29","cited_by_count":106,"area":null},{"id":"2202.14026","title":"Robust Training under Label Noise by Over-parameterization","created":"2022-02-28","cited_by_count":93,"area":null},{"id":"2206.07085","title":"Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction","created":"2022-06-14","cited_by_count":86,"area":null},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74,"area":null},{"id":"2306.07042","title":"Transformers learn through gradual rank increase","created":"2023-06-12","cited_by_count":52,"area":null},{"id":"2301.11500","title":"Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing","created":"2023-01-27","cited_by_count":42,"area":null},{"id":"2207.04036","title":"Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent","created":"2022-07-08","cited_by_count":39,"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":"2601.13474","title":"Preconditioning Benefits of Spectral Orthogonalization in Muon","created":"2026-01-20","cited_by_count":30,"area":null},{"id":"2307.12851","title":"Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization","created":"2023-07-24","cited_by_count":28,"area":null},{"id":"2406.04112","title":"Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2112.11027","title":"More is Less: Inducing Sparsity via Overparameterization","created":"2021-12-21","cited_by_count":24,"area":null},{"id":"2408.03733","title":"Bayes-optimal learning of an extensive-width neural network from quadratically many samples","created":"2024-08-07","cited_by_count":23,"area":null},{"id":"2202.08788","title":"Global Convergence of Sub-gradient Method for Robust Matrix Recovery: Small Initialization, Noisy Measurements, and Over-parameterization","created":"2022-02-17","cited_by_count":21,"area":null},{"id":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20,"area":null},{"id":"2403.08699","title":"Implicit Regularization of Gradient Flow on One-Layer Softmax Attention","created":"2024-03-13","cited_by_count":19,"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":"2206.08756","title":"Tensor-on-Tensor Regression: Riemannian Optimization, Over-parameterization, Statistical-computational Gap, and Their Interplay","created":"2022-06-17","cited_by_count":15,"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":"2310.12408","title":"Provable Guarantees for Neural Networks via Gradient Feature Learning","created":"2023-10-19","cited_by_count":14,"area":null},{"id":"2506.06489","title":"Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks","created":"2025-06-06","cited_by_count":14,"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":"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":"2305.05448","title":"Robust Implicit Regularization via Weight Normalization","created":"2023-05-09","cited_by_count":12,"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":"2506.10887","title":"Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers","created":"2025-06-12","cited_by_count":10,"area":"lr"},{"id":"2510.06954","title":"From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics","created":"2025-10-08","cited_by_count":10,"area":null},{"id":"2209.10675","title":"A Validation Approach to Over-parameterized Matrix and Image Recovery","created":"2022-09-21","cited_by_count":8,"area":null},{"id":"2308.15461","title":"Canonical Factors for Hybrid Neural Fields","created":"2023-08-29","cited_by_count":8,"area":null},{"id":"2401.02592","title":"Guaranteed Nonconvex Factorization Approach for Tensor Train Recovery","created":"2024-01-05","cited_by_count":8,"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":"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":"2306.13239","title":"The Inductive Bias of Flatness Regularization for Deep Matrix Factorization","created":"2023-06-22","cited_by_count":6,"area":null},{"id":"2310.06159","title":"Provably Accelerating Ill-Conditioned Low-rank Estimation via Scaled Gradient Descent, Even with Overparameterization","created":"2023-10-09","cited_by_count":6,"area":null},{"id":"2402.06756","title":"Convergence of Gradient Descent with Small Initialization for Unregularized Matrix Completion","created":"2024-02-09","cited_by_count":6,"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":"2405.15942","title":"Can Implicit Bias Imply Adversarial Robustness?","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2410.08309","title":"Swing-by Dynamics in Concept Learning and Compositional Generalization","created":"2024-10-10","cited_by_count":5,"area":"diffusion"},{"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":"2307.07410","title":"Implicit regularization in AI meets generalized hardness of approximation in optimization -- Sharp results for diagonal linear networks","created":"2023-07-13","cited_by_count":4,"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":"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":"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":"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":"2212.12086","title":"Eigenvalue initialisation and regularisation for Koopman autoencoders","created":"2022-12-23","cited_by_count":2,"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":"2410.15224","title":"Robust Low-rank Tensor Train Recovery","created":"2024-10-19","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":"2606.21514","title":"Towards Understanding the Power and Limits of the Muon Optimizer: A River-Valley Perspective","created":"2026-06-19","cited_by_count":2,"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":"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":"2606.04476","title":"When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2202.09276","title":"Geometric Regularization from Overparameterization","created":"2022-02-18","cited_by_count":0,"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":"2402.18805","title":"VEC-SBM: Optimal Community Detection with Vectorial Edges Covariates","created":"2024-02-29","cited_by_count":0,"area":null},{"id":"2410.20248","title":"Convergence Guarantees for the DeepWalk Embedding on Block Models","created":"2024-10-26","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":"2502.00320","title":"$k$-SVD with Gradient Descent","created":"2025-02-01","cited_by_count":0,"area":null},{"id":"2602.00827","title":"Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.01267","title":"Diving into Kronecker Adapters: Component Design Matters","created":"2026-02-01","cited_by_count":0,"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":"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},{"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":"2605.25612","title":"Towards the Connection between Activation Sparsity and Flat Minima","created":"2026-05-25","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":"2610.18318","title":"Over-parameterization Is Neither Robust nor Fragile in Matrix Sensing: A Geometric Theory of Solution Robustness","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}