{"total":156,"rows":[{"id":"2102.07078","title":"Exploiting Shared Representations for Personalized Federated Learning","created":"2021-02-14","cited_by_count":541,"area":null},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337,"area":null},{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"id":"2111.12444","title":"Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications","created":"2021-11-24","cited_by_count":97,"area":null},{"id":"2203.01238","title":"On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features","created":"2022-03-02","cited_by_count":97,"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":"2210.02192","title":"Are All Losses Created Equal: A Neural Collapse Perspective","created":"2022-10-04","cited_by_count":78,"area":null},{"id":"2102.09972","title":"Implicit Regularization in Tensor Factorization","created":"2021-02-19","cited_by_count":44,"area":null},{"id":"2302.02774","title":"The SSL Interplay: Augmentations, Inductive Bias, and Generalization","created":"2023-02-06","cited_by_count":40,"area":null},{"id":"2303.15438","title":"On the Stepwise Nature of Self-Supervised Learning","created":"2023-03-27","cited_by_count":36,"area":null},{"id":"2210.16658","title":"Perturbation Analysis of Neural Collapse","created":"2022-10-29","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":"2103.01519","title":"Hessian Eigenspectra of More Realistic Nonlinear Models","created":"2021-03-02","cited_by_count":33,"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":"2601.13474","title":"Preconditioning Benefits of Spectral Orthogonalization in Muon","created":"2026-01-20","cited_by_count":30,"area":null},{"id":"2104.14526","title":"Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Estimation from Incomplete Measurements","created":"2021-04-29","cited_by_count":28,"area":null},{"id":"2108.01538","title":"Geometry of Linear Convolutional Networks","created":"2021-08-03","cited_by_count":27,"area":null},{"id":"2111.01875","title":"Subquadratic Overparameterization for Shallow Neural Networks","created":"2021-11-02","cited_by_count":26,"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":"2310.11028","title":"Matrix Compression via Randomized Low Rank and Low Precision Factorization","created":"2023-10-17","cited_by_count":25,"area":null},{"id":"2109.11154","title":"Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery","created":"2021-09-23","cited_by_count":22,"area":null},{"id":"2107.12365","title":"Inference for Heteroskedastic PCA with Missing Data","created":"2021-07-26","cited_by_count":21,"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":"2306.01154","title":"The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2110.04926","title":"Convergence of Random Reshuffling Under The Kurdyka-{\\L}ojasiewicz Inequality","created":"2021-10-10","cited_by_count":16,"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":"2407.06172","title":"On Speeding Up Language Model Evaluation","created":"2024-07-08","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":"2109.12701","title":"Sparse Plus Low Rank Matrix Decomposition: A Discrete Optimization Approach","created":"2021-09-26","cited_by_count":14,"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":"2106.02119","title":"A Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few Samples","created":"2021-06-03","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":"2406.01909","title":"A Global Geometric Analysis of Maximal Coding Rate Reduction","created":"2024-06-04","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":"2207.01578","title":"Quantum Neural Network Compression","created":"2022-07-04","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":"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":"2206.09109","title":"Fast and Provable Tensor Robust Principal Component Analysis via Scaled Gradient Descent","created":"2022-06-18","cited_by_count":11,"area":null},{"id":"2310.00526","title":"Are Graph Neural Networks Optimal Approximation Algorithms?","created":"2023-10-01","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":"2112.10467","title":"An iterative clustering algorithm for the Contextual Stochastic Block Model with optimality guarantees","created":"2021-12-20","cited_by_count":10,"area":null},{"id":"2302.03682","title":"Approximate message passing from random initialization with applications to $\\mathbb{Z}_{2}$ synchronization","created":"2023-02-07","cited_by_count":9,"area":null},{"id":"2305.18436","title":"Statistically Optimal K-means Clustering via Nonnegative Low-rank Semidefinite Programming","created":"2023-05-29","cited_by_count":9,"area":null},{"id":"2502.04700","title":"EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inference","created":"2025-02-07","cited_by_count":9,"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":"2212.08642","title":"Estimating Higher-Order Mixed Memberships via the $\\ell_{2,\\infty}$ Tensor Perturbation Bound","created":"2022-12-16","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":"2303.02732","title":"Iterative Approximate Cross-Validation","created":"2023-03-05","cited_by_count":7,"area":null},{"id":"2306.08173","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2306.14522","title":"Nonconvex Stochastic Bregman Proximal Gradient Method with Application to Deep Learning","created":"2023-06-26","cited_by_count":7,"area":null},{"id":"2104.08928","title":"Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings","created":"2021-04-18","cited_by_count":6,"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":"2211.15482","title":"Discovering Dynamic Patterns from Spatiotemporal Data with Time-Varying Low-Rank Autoregression","created":"2022-11-28","cited_by_count":6,"area":null},{"id":"2302.07851","title":"Continuized Acceleration for Quasar Convex Functions in Non-Convex Optimization","created":"2023-02-15","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":"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":"2105.12257","title":"Rank-one matrix estimation: analytic time evolution of gradient descent dynamics","created":"2021-05-25","cited_by_count":5,"area":null},{"id":"2203.10651","title":"Forecasting Sparse Movement Speed of Urban Road Networks with Nonstationary Temporal Matrix Factorization","created":"2022-03-20","cited_by_count":5,"area":null},{"id":"2311.11841","title":"High Probability Guarantees for Random Reshuffling","created":"2023-11-20","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":"2505.18698","title":"MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention","created":"2025-05-24","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":"2201.07401","title":"Multiway Spherical Clustering via Degree-Corrected Tensor Block Models","created":"2022-01-19","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":"2204.04099","title":"Seeded graph matching for the correlated Gaussian Wigner model via the projected power method","created":"2022-04-08","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":"2210.05355","title":"Multi-User Reinforcement Learning with Low Rank Rewards","created":"2022-10-11","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":"2306.00342","title":"Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networks","created":"2023-06-01","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":"2406.06002","title":"Computational and Statistical Guarantees for Tensor-on-Tensor Regression with Tensor Train Decomposition","created":"2024-06-10","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":"2506.05387","title":"Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs","created":"2025-06-03","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":"2307.13818","title":"Gradient-Based Spectral Embeddings of Random Dot Product Graphs","created":"2023-07-25","cited_by_count":3,"area":null},{"id":"2309.04788","title":"Stochastic Gradient Descent outperforms Gradient Descent in recovering a high-dimensional signal in a glassy energy landscape","created":"2023-09-09","cited_by_count":3,"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":"2402.03648","title":"Multilinear Kernel Regression and Imputation via Manifold Learning","created":"2024-02-06","cited_by_count":3,"area":null},{"id":"2402.04751","title":"Asymptotic Dynamics of Alternating Minimization for Bilinear Regression","created":"2024-02-07","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":"2409.01362","title":"Correlating Time Series with Interpretable Convolutional Kernels","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2410.16982","title":"Sample-Efficient Geometry Reconstruction from Euclidean Distances using Non-Convex Optimization","created":"2024-10-22","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":"2604.21905","title":"Low-Rank Adaptation Redux for Large Models","created":"2026-04-23","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":"2101.07354","title":"Exact Recovery of Community Structures Using DeepWalk and Node2vec","created":"2021-01-18","cited_by_count":2,"area":null},{"id":"2104.10314","title":"Efficient Sparse Coding using Hierarchical Riemannian Pursuit","created":"2021-04-21","cited_by_count":2,"area":null},{"id":"2301.04204","title":"A Newton-CG based barrier-augmented Lagrangian method for general nonconvex conic optimization","created":"2023-01-10","cited_by_count":2,"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":"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":"2310.00729","title":"Spectral Neural Networks: Approximation Theory and Optimization Landscape","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2404.17592","title":"Low-Rank Online Dynamic Assortment with Dual Contextual Information","created":"2024-04-19","cited_by_count":2,"area":null},{"id":"2411.02098","title":"Low-Rank Tensors for Multi-Dimensional Markov Models","created":"2024-11-04","cited_by_count":2,"area":null}],"next_cursor":"100"}