{"total":59,"rows":[{"id":"2112.00029","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","created":"2021-11-30","cited_by_count":76,"area":null},{"id":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62,"area":null},{"id":"2303.16504","title":"An Over-parameterized Exponential Regression","created":"2023-03-29","cited_by_count":45,"area":null},{"id":"2101.09612","title":"On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths","created":"2021-01-24","cited_by_count":44,"area":null},{"id":"2205.10217","title":"Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization","created":"2022-05-20","cited_by_count":36,"area":null},{"id":"2106.05932","title":"Early-stopped neural networks are consistent","created":"2021-06-10","cited_by_count":34,"area":null},{"id":"2108.09420","title":"Fast Sketching of Polynomial Kernels of Polynomial Degree","created":"2021-08-21","cited_by_count":33,"area":null},{"id":"2110.04622","title":"Does Preprocessing Help Training Over-parameterized Neural Networks?","created":"2021-10-09","cited_by_count":32,"area":null},{"id":"2211.14227","title":"Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing","created":"2022-11-25","cited_by_count":29,"area":null},{"id":"2111.01875","title":"Subquadratic Overparameterization for Shallow Neural Networks","created":"2021-11-02","cited_by_count":26,"area":null},{"id":"2308.12247","title":"How to Protect Copyright Data in Optimization of Large Language Models?","created":"2023-08-23","cited_by_count":26,"area":null},{"id":"2406.12839","title":"Evaluating the design space of diffusion-based generative models","created":"2024-06-18","cited_by_count":26,"area":"diffusion"},{"id":"2208.13614","title":"Neural Tangent Kernel: A Survey","created":"2022-08-29","cited_by_count":23,"area":null},{"id":"2208.04508","title":"Training Overparametrized Neural Networks in Sublinear Time","created":"2022-08-09","cited_by_count":22,"area":null},{"id":"2208.05395","title":"A Sublinear Adversarial Training Algorithm","created":"2022-08-10","cited_by_count":22,"area":null},{"id":"2109.09304","title":"Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks","created":"2021-09-20","cited_by_count":21,"area":null},{"id":"2308.13431","title":"Six Lectures on Linearized Neural Networks","created":"2023-08-25","cited_by_count":20,"area":null},{"id":"2401.07187","title":"A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models","created":"2024-01-14","cited_by_count":20,"area":null},{"id":"2208.03635","title":"Federated Adversarial Learning: A Framework with Convergence Analysis","created":"2022-08-07","cited_by_count":17,"area":null},{"id":"2206.12802","title":"Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis","created":"2022-06-26","cited_by_count":15,"area":null},{"id":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"area":null},{"id":"2405.03251","title":"Exploring the Frontiers of Softmax: Provable Optimization, Applications in Diffusion Model, and Beyond","created":"2024-05-06","cited_by_count":15,"area":"diffusion"},{"id":"2407.13621","title":"Differential Privacy Mechanisms in Neural Tangent Kernel Regression","created":"2024-07-18","cited_by_count":14,"area":null},{"id":"2105.05001","title":"FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Convergence Analysis","created":"2021-05-11","cited_by_count":13,"area":null},{"id":"2310.12462","title":"Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights","created":"2023-10-19","cited_by_count":12,"area":null},{"id":"2112.02668","title":"On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons","created":"2021-12-05","cited_by_count":11,"area":null},{"id":"2307.06565","title":"Efficient SGD Neural Network Training via Sublinear Activated Neuron Identification","created":"2023-07-13","cited_by_count":11,"area":null},{"id":"2102.10424","title":"GIST: Distributed Training for Large-Scale Graph Convolutional Networks","created":"2021-02-20","cited_by_count":10,"area":null},{"id":"2309.08044","title":"How many Neurons do we need? A refined Analysis for Shallow Networks trained with Gradient Descent","created":"2023-09-14","cited_by_count":10,"area":null},{"id":"2406.14036","title":"Towards Infinite-Long Prefix in Transformer","created":"2024-06-20","cited_by_count":10,"area":null},{"id":"2201.04738","title":"Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks","created":"2022-01-12","cited_by_count":9,"area":null},{"id":"2307.14531","title":"Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum","created":"2023-07-26","cited_by_count":9,"area":null},{"id":"2310.11291","title":"An Automatic Learning Rate Schedule Algorithm for Achieving Faster Convergence and Steeper Descent","created":"2023-10-17","cited_by_count":9,"area":null},{"id":"2107.01832","title":"Provable Convergence of Nesterov's Accelerated Gradient Method for Over-Parameterized Neural Networks","created":"2021-07-05","cited_by_count":7,"area":null},{"id":"2209.08399","title":"Approximation results for Gradient Descent trained Shallow Neural Networks in $1d$","created":"2022-09-17","cited_by_count":7,"area":null},{"id":"2308.08358","title":"Convergence of Two-Layer Regression with Nonlinear Units","created":"2023-08-16","cited_by_count":6,"area":null},{"id":"2311.13624","title":"A Theoretical Insight into Attack and Defense of Gradient Leakage in Transformer","created":"2023-11-22","cited_by_count":6,"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":"2303.04555","title":"Streaming Kernel PCA Algorithm With Small Space","created":"2023-03-08","cited_by_count":5,"area":null},{"id":"2305.08001","title":"Structured and Fast Optimization: The Kronecker SGD Algorithm","created":"2023-05-13","cited_by_count":5,"area":null},{"id":"2308.02001","title":"Memory capacity of two layer neural networks with smooth activations","created":"2023-08-03","cited_by_count":5,"area":null},{"id":"2101.04243","title":"A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks","created":"2021-01-12","cited_by_count":4,"area":null},{"id":"2306.03356","title":"Query Complexity of Active Learning for Function Family With Nearly Orthogonal Basis","created":"2023-06-06","cited_by_count":4,"area":null},{"id":"2307.13962","title":"Understanding Deep Neural Networks via Linear Separability of Hidden Layers","created":"2023-07-26","cited_by_count":4,"area":null},{"id":"2411.01663","title":"Unlocking the Theory Behind Scaling 1-Bit Neural Networks","created":"2024-11-03","cited_by_count":4,"area":null},{"id":"2301.00335","title":"Pruning Before Training May Improve Generalization, Provably","created":"2023-01-01","cited_by_count":3,"area":null},{"id":"2402.04783","title":"Analyzing the Neural Tangent Kernel of Periodically Activated Coordinate Networks","created":"2024-02-07","cited_by_count":3,"area":null},{"id":"2407.02827","title":"Convergence of Implicit Gradient Descent for Training Two-Layer Physics-Informed Neural Networks","created":"2024-07-03","cited_by_count":3,"area":null},{"id":"2112.02446","title":"Fast Graph Neural Tangent Kernel via Kronecker Sketching","created":"2021-12-04","cited_by_count":2,"area":null},{"id":"2301.00327","title":"Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK","created":"2023-01-01","cited_by_count":2,"area":null},{"id":"2309.04860","title":"Approximation Results for Gradient Descent trained Neural Networks","created":"2023-09-09","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":"2606.23364","title":"Convergence of Gradient Descent for General Neural Network Architectures Beyond the NTK Regime","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2212.02323","title":"Improved Convergence Guarantees for Shallow Neural Networks","created":"2022-12-05","cited_by_count":1,"area":null},{"id":"2405.11696","title":"Approximation and Gradient Descent Training with Neural Networks","created":"2024-05-19","cited_by_count":1,"area":null},{"id":"2506.24120","title":"Data Uniformity Improves Training Efficiency and More, with a Convergence Framework Beyond the NTK Regime","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2206.03254","title":"Demystifying the Global Convergence Puzzle of Learning Over-parameterized ReLU Nets in Very High Dimensions","created":"2022-06-05","cited_by_count":0,"area":null},{"id":"2208.03941","title":"Provable Acceleration of Nesterov's Accelerated Gradient Method over Heavy Ball Method in Training Over-Parameterized Neural Networks","created":"2022-08-08","cited_by_count":0,"area":null},{"id":"2310.05495","title":"On the Convergence of Federated Averaging under Partial Participation for Over-parameterized Neural Networks","created":"2023-10-09","cited_by_count":0,"area":null}],"next_cursor":null}