{"total":45,"rows":[{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"id":"2210.15651","title":"Learning Single-Index Models with Shallow Neural Networks","created":"2022-10-27","cited_by_count":92,"area":null},{"id":"2206.00939","title":"Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs","created":"2022-06-02","cited_by_count":76,"area":null},{"id":"2209.14863","title":"Neural Networks Efficiently Learn Low-Dimensional Representations with SGD","created":"2022-09-29","cited_by_count":63,"area":null},{"id":"2206.01717","title":"A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features","created":"2022-06-03","cited_by_count":49,"area":null},{"id":"2310.12680","title":"On the Optimization and Generalization of Multi-head Attention","created":"2023-10-19","cited_by_count":37,"area":null},{"id":"2302.10034","title":"Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron","created":"2023-02-20","cited_by_count":25,"area":null},{"id":"2112.12982","title":"Parameter identifiability of a deep feedforward ReLU neural network","created":"2021-12-24","cited_by_count":24,"area":null},{"id":"2205.09072","title":"On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias","created":"2022-05-18","cited_by_count":21,"area":null},{"id":"2209.07263","title":"Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)","created":"2022-09-15","cited_by_count":18,"area":null},{"id":"2110.08084","title":"Gradient Descent on Infinitely Wide Neural Networks: Global Convergence and Generalization","created":"2021-10-15","cited_by_count":16,"area":null},{"id":"2307.06887","title":"Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks","created":"2023-07-13","cited_by_count":16,"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":"2407.13621","title":"Differential Privacy Mechanisms in Neural Tangent Kernel Regression","created":"2024-07-18","cited_by_count":14,"area":null},{"id":"2204.10782","title":"On Feature Learning in Neural Networks with Global Convergence Guarantees","created":"2022-04-22","cited_by_count":13,"area":null},{"id":"2110.06488","title":"The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program","created":"2021-10-13","cited_by_count":11,"area":null},{"id":"2402.03625","title":"Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2306.05674","title":"Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks","created":"2023-06-09","cited_by_count":10,"area":null},{"id":"2107.12910","title":"Sparse Bayesian Deep Learning for Dynamic System Identification","created":"2021-07-27","cited_by_count":9,"area":null},{"id":"2304.01063","title":"Depth Separation with Multilayer Mean-Field Networks","created":"2023-04-03","cited_by_count":9,"area":null},{"id":"2210.12001","title":"When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work","created":"2022-10-21","cited_by_count":8,"area":null},{"id":"2107.14324","title":"Deep Networks Provably Classify Data on Curves","created":"2021-07-29","cited_by_count":6,"area":null},{"id":"2206.02139","title":"Early Stage Convergence and Global Convergence of Training Mildly Parameterized Neural Networks","created":"2022-06-05","cited_by_count":5,"area":null},{"id":"2209.00771","title":"Optimizing the Performative Risk under Weak Convexity Assumptions","created":"2022-09-02","cited_by_count":5,"area":null},{"id":"2210.11452","title":"Global Convergence of SGD On Two Layer Neural Nets","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2211.04589","title":"Finite Sample Identification of Wide Shallow Neural Networks with Biases","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2409.02718","title":"\"Yes, My LoRD.\" Guiding Language Model Extraction with Locality Reinforced Distillation","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2305.00322","title":"Toward $L_\\infty$-recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields","created":"2023-04-29","cited_by_count":4,"area":null},{"id":"2406.01766","title":"How Does Gradient Descent Learn Features -- A Local Analysis for Regularized Two-Layer Neural Networks","created":"2024-06-03","cited_by_count":4,"area":null},{"id":"2208.09529","title":"Intersection of Parallels as an Early Stopping Criterion","created":"2022-08-19","cited_by_count":3,"area":null},{"id":"2309.09258","title":"Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets","created":"2023-09-17","cited_by_count":3,"area":null},{"id":"2502.16977","title":"Convergence of Shallow ReLU Networks on Weakly Interacting Data","created":"2025-02-24","cited_by_count":2,"area":null},{"id":"2504.21501","title":"Deep Learning Optimization Using Self-Adaptive Weighted Auxiliary Variables","created":"2025-04-30","cited_by_count":2,"area":null},{"id":"2512.22088","title":"Unifying Learning Dynamics and Generalization in Transformers Scaling Law","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2206.05562","title":"Parameter Convex Neural Networks","created":"2022-06-11","cited_by_count":1,"area":null},{"id":"2308.04753","title":"SAfER: Layer-Level Sensitivity Assessment for Efficient and Robust Neural Network Inference","created":"2023-08-09","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":"2502.05360","title":"Curse of Dimensionality in Neural Network Optimization","created":"2025-02-07","cited_by_count":1,"area":null},{"id":"2503.10428","title":"Langevin Monte-Carlo Provably Learns Depth Two Neural Nets at Any Size and Data","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2507.21429","title":"From Sublinear to Linear: Local Convergence in Finite-Width Networks via Locally Polyak-Lojasiewicz Regions","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2509.16959","title":"Graph Coloring for Multi-Task Learning","created":"2025-09-21","cited_by_count":1,"area":null},{"id":"2608.06766","title":"Hidden Gauge Controls Feature Specialization in ReLU Networks","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2510.19382","title":"A Derandomization Framework for Structure Discovery: Applications in Neural Networks and Beyond","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2604.23225","title":"A Layer Separation Optimization Framework for Cross-Entropy Training in Deep Learning","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2610.01728","title":"Removing spurious minima for planar features by skip connections","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}