{"total":96,"rows":[{"id":"2102.07078","title":"Exploiting Shared Representations for Personalized Federated Learning","created":"2021-02-14","cited_by_count":541,"area":null},{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154,"area":null},{"id":"2303.09105","title":"Rethinking Model Ensemble in Transfer-based Adversarial Attacks","created":"2023-03-16","cited_by_count":89,"area":null},{"id":"2106.15013","title":"Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction","created":"2021-06-28","cited_by_count":78,"area":null},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74,"area":null},{"id":"2209.05423","title":"Statistical Learning Theory for Control: A Finite Sample Perspective","created":"2022-09-12","cited_by_count":53,"area":null},{"id":"2110.03677","title":"Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect","created":"2021-10-07","cited_by_count":50,"area":null},{"id":"2106.14289","title":"Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization","created":"2021-06-27","cited_by_count":45,"area":null},{"id":"2102.09972","title":"Implicit Regularization in Tensor Factorization","created":"2021-02-19","cited_by_count":44,"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":"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":"2102.02756","title":"On the computational and statistical complexity of over-parameterized matrix sensing","created":"2021-01-27","cited_by_count":31,"area":null},{"id":"2206.03345","title":"Preconditioned Gradient Descent for Overparameterized Nonconvex Burer--Monteiro Factorization with Global Optimality Certification","created":"2022-06-07","cited_by_count":21,"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":"2102.12430","title":"Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization","created":"2021-02-24","cited_by_count":15,"area":null},{"id":"2303.12298","title":"A General Algorithm for Solving Rank-one Matrix Sensing","created":"2023-03-22","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":"2104.12031","title":"Low-rank Tensor Estimation via Riemannian Gauss-Newton: Statistical Optimality and Second-Order Convergence","created":"2021-04-24","cited_by_count":13,"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":"2305.06927","title":"Convergence of Alternating Gradient Descent for Matrix Factorization","created":"2023-05-11","cited_by_count":12,"area":null},{"id":"2504.09708","title":"Preconditioned Gradient Descent for Over-Parameterized Nonconvex Matrix Factorization","created":"2025-04-13","cited_by_count":12,"area":null},{"id":"2105.13831","title":"Implicit Regularization in Matrix Sensing via Mirror Descent","created":"2021-05-28","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":"2106.12933","title":"GNMR: A provable one-line algorithm for low rank matrix recovery","created":"2021-06-24","cited_by_count":10,"area":null},{"id":"2410.14802","title":"Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems","created":"2024-10-18","cited_by_count":10,"area":null},{"id":"2203.03899","title":"Noisy Low-rank Matrix Optimization: Geometry of Local Minima and Convergence Rate","created":"2022-03-08","cited_by_count":8,"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":"2401.02592","title":"Guaranteed Nonconvex Factorization Approach for Tensor Train Recovery","created":"2024-01-05","cited_by_count":8,"area":null},{"id":"2105.08232","title":"Sharp Restricted Isometry Property Bounds for Low-rank Matrix Recovery Problems with Corrupted Measurements","created":"2021-05-18","cited_by_count":7,"area":null},{"id":"2202.01625","title":"Efficient learning of hidden state LTI state space models of unknown order","created":"2022-02-03","cited_by_count":7,"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":"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":"2110.10279","title":"Factorization Approach for Low-complexity Matrix Completion Problems: Exponential Number of Spurious Solutions and Failure of Gradient Methods","created":"2021-10-19","cited_by_count":6,"area":null},{"id":"2208.11246","title":"Accelerating SGD for Highly Ill-Conditioned Huge-Scale Online Matrix Completion","created":"2022-08-24","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":"2409.16499","title":"Learning Linear Dynamics from Bilinear Observations","created":"2024-09-24","cited_by_count":6,"area":null},{"id":"2104.07006","title":"Fast quantum state reconstruction via accelerated non-convex programming","created":"2021-04-14","cited_by_count":5,"area":null},{"id":"2104.10790","title":"Sharp Global Guarantees for Nonconvex Low-rank Recovery in the Noisy Overparameterized Regime","created":"2021-04-21","cited_by_count":5,"area":null},{"id":"2305.09145","title":"Deep ReLU Networks Have Surprisingly Simple Polytopes","created":"2023-05-16","cited_by_count":5,"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":"2502.04043","title":"Probe-Free Low-Rank Activation Intervention","created":"2025-02-06","cited_by_count":5,"area":null},{"id":"2603.01514","title":"Training Dynamics of Softmax Self-Attention: Fast Global Convergence via Preconditioning","created":"2026-03-02","cited_by_count":5,"area":null},{"id":"2107.00371","title":"Sparse GCA and Thresholded Gradient Descent","created":"2021-07-01","cited_by_count":4,"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":"2201.13052","title":"Inductive Matrix Completion: No Bad Local Minima and a Fast Algorithm","created":"2022-01-31","cited_by_count":4,"area":null},{"id":"2206.04276","title":"Robust Matrix Completion with Heavy-tailed Noise","created":"2022-06-09","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":"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":"2309.09032","title":"Solving Quadratic Systems with Full-Rank Matrices Using Sparse or Generative Priors","created":"2023-09-16","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":"2506.16032","title":"A Scalable Factorization Approach for High-Order Structured Tensor Recovery","created":"2025-06-19","cited_by_count":4,"area":null},{"id":"2110.12121","title":"On Geometric Connections of Embedded and Quotient Geometries in Riemannian Fixed-rank Matrix Optimization","created":"2021-10-23","cited_by_count":3,"area":null},{"id":"2209.13762","title":"Consensus Knowledge Graph Learning via Multi-view Sparse Low Rank Block Model","created":"2022-09-28","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":"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":"2101.05113","title":"Beyond Procrustes: Balancing-Free Gradient Descent for Asymmetric Low-Rank Matrix Sensing","created":"2021-01-13","cited_by_count":2,"area":null},{"id":"2106.00293","title":"A Non-commutative Extension of Lee-Seung's Algorithm for Positive Semidefinite Factorizations","created":"2021-06-01","cited_by_count":2,"area":null},{"id":"2109.02703","title":"Large-Scale System Identification Using a Randomized SVD","created":"2021-09-06","cited_by_count":2,"area":null},{"id":"2205.13827","title":"Error Bound of Empirical $\\ell_2$ Risk Minimization for Noisy Standard and Generalized Phase Retrieval Problems","created":"2022-05-27","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":"2311.11182","title":"Exponentially Convergent Algorithms for Supervised Matrix Factorization","created":"2023-11-18","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":"2410.15224","title":"Robust Low-rank Tensor Train Recovery","created":"2024-10-19","cited_by_count":2,"area":null},{"id":"2505.07272","title":"ALPCAH: Subspace Learning for Sample-wise Heteroscedastic Data","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2506.03230","title":"DiaBlo: Diagonal Blocks Are Sufficient For Finetuning","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2510.13406","title":"When Embedding Models Meet: Procrustes Bounds and Applications","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2101.00236","title":"On Stochastic Variance Reduced Gradient Method for Semidefinite Optimization","created":"2021-01-01","cited_by_count":1,"area":null},{"id":"2105.12022","title":"Principal Component Hierarchy for Sparse Quadratic Programs","created":"2021-05-25","cited_by_count":1,"area":null},{"id":"2203.11579","title":"Local Stochastic Factored Gradient Descent for Distributed Quantum State Tomography","created":"2022-03-22","cited_by_count":1,"area":null},{"id":"2205.03059","title":"Low-rank Tensor Learning with Nonconvex Overlapped Nuclear Norm Regularization","created":"2022-05-06","cited_by_count":1,"area":null},{"id":"2206.06774","title":"Supervised Dictionary Learning with Auxiliary Covariates","created":"2022-06-14","cited_by_count":1,"area":null},{"id":"2311.14658","title":"Convergence Analysis for Learning Orthonormal Deep Linear Neural Networks","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2407.19446","title":"Leave-One-Out Analysis for Nonconvex Robust Matrix Completion with General Thresholding Functions","created":"2024-07-28","cited_by_count":1,"area":null},{"id":"2411.19468","title":"Learning Expressive Random Feature Models via Parametrized Activations","created":"2024-11-29","cited_by_count":1,"area":null},{"id":"2510.15327","title":"On the Generalization Properties of Learning the Random Feature Models with Learnable Activation Functions","created":"2025-10-17","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":"2201.01689","title":"Asymptotics of $\\ell_2$ Regularized Network Embeddings","created":"2022-01-05","cited_by_count":0,"area":null},{"id":"2310.17712","title":"Community Detection Guarantees Using Embeddings Learned by Node2Vec","created":"2023-10-26","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":"2506.18282","title":"Phase retrieval with rank $d$ measurements -- \\emph{descending} algorithms phase transitions","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2511.07438","title":"Two Datasets Are Better Than One: Method of Double Moments for 3-D Reconstruction in Cryo-EM","created":"2025-11-02","cited_by_count":0,"area":null},{"id":"2602.07218","title":"Collaborative and Efficient Fine-tuning: Leveraging Task Similarity","created":"2026-02-06","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":"2603.07437","title":"Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II","created":"2026-03-08","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":"2604.13393","title":"A short proof of near-linear convergence of adaptive gradient descent under fourth-order growth and convexity","created":"2026-04-15","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":"2605.08734","title":"AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.10741","title":"AdaPaD: Adaptive Parallel Deflation for PEFT with Self-Correcting Rank Discovery","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.28613","title":"Stability of Low-Rank Implicit Regularization in Perturbed Deep Matrix Factorization","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.00934","title":"Efficient Synthetic Network Generation via Latent Embedding Reconstruction","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.12691","title":"Two-Layer Linear Auto-Regressive Models Estimate Latent States","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2609.37865","title":"Strict-Saddle Landscapes and Multi-Rank Geometry in Low-Tubal-Rank Tensor Sensing","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}