{"total":84,"rows":[{"id":"2105.15134","title":"Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning","created":"2021-05-31","cited_by_count":119,"area":null},{"id":"2202.06526","title":"Benign Overfitting in Two-layer Convolutional Neural Networks","created":"2022-02-14","cited_by_count":91,"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":"2110.13905","title":"Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias","created":"2021-10-26","cited_by_count":83,"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":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62,"area":null},{"id":"2106.01606","title":"Exploring Memorization in Adversarial Training","created":"2021-06-03","cited_by_count":55,"area":null},{"id":"2108.11371","title":"Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization","created":"2021-08-25","cited_by_count":49,"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":"2206.02768","title":"The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization","created":"2022-06-06","cited_by_count":41,"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":"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":"2402.15926","title":"Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency","created":"2024-02-24","cited_by_count":35,"area":null},{"id":"2106.05932","title":"Early-stopped neural networks are consistent","created":"2021-06-10","cited_by_count":34,"area":null},{"id":"2106.04013","title":"The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization","created":"2021-06-07","cited_by_count":33,"area":null},{"id":"2105.10585","title":"Properties of the After Kernel","created":"2021-05-21","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":"2305.14077","title":"Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension","created":"2023-05-23","cited_by_count":26,"area":null},{"id":"2302.09235","title":"Generalization and Stability of Interpolating Neural Networks with Minimal Width","created":"2023-02-18","cited_by_count":21,"area":null},{"id":"2101.04844","title":"Reproducing Activation Function for Deep Learning","created":"2021-01-13","cited_by_count":19,"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":"2101.01152","title":"Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise","created":"2021-01-04","cited_by_count":17,"area":null},{"id":"2201.09910","title":"Learning Neural Contextual Bandits Through Perturbed Rewards","created":"2022-01-24","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":"2103.11488","title":"The Discovery of Dynamics via Linear Multistep Methods and Deep Learning: Error Estimation","created":"2021-03-21","cited_by_count":14,"area":null},{"id":"2108.00207","title":"The Separation Capacity of Random Neural Networks","created":"2021-07-31","cited_by_count":14,"area":null},{"id":"2208.02789","title":"Feature selection with gradient descent on two-layer networks in low-rotation regimes","created":"2022-08-04","cited_by_count":14,"area":null},{"id":"2209.07238","title":"Generalization Properties of NAS under Activation and Skip Connection Search","created":"2022-09-15","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":"2110.11280","title":"Actor-critic is implicitly biased towards high entropy optimal policies","created":"2021-10-21","cited_by_count":13,"area":null},{"id":"2311.01575","title":"On the Convergence of Encoder-only Shallow Transformers","created":"2023-11-02","cited_by_count":13,"area":null},{"id":"2105.06569","title":"The Dynamics of Gradient Descent for Overparametrized Neural Networks","created":"2021-05-13","cited_by_count":11,"area":null},{"id":"2305.19377","title":"Benign Overfitting in Deep Neural Networks under Lazy Training","created":"2023-05-30","cited_by_count":10,"area":null},{"id":"2109.03992","title":"Stationary Density Estimation of It\\^o Diffusions Using Deep Learning","created":"2021-09-09","cited_by_count":9,"area":null},{"id":"2202.02710","title":"Spectrally Adapted Physics-Informed Neural Networks for Solving Unbounded Domain Problems","created":"2022-02-06","cited_by_count":9,"area":null},{"id":"2202.12262","title":"On the Omnipresence of Spurious Local Minima in Certain Neural Network Training Problems","created":"2022-02-23","cited_by_count":8,"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":"2403.12887","title":"Understanding the training of infinitely deep and wide ResNets with Conditional Optimal Transport","created":"2024-03-19","cited_by_count":8,"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":"2410.10024","title":"Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods","created":"2024-10-13","cited_by_count":7,"area":null},{"id":"2107.14324","title":"Deep Networks Provably Classify Data on Curves","created":"2021-07-29","cited_by_count":6,"area":null},{"id":"2109.14142","title":"On the Provable Generalization of Recurrent Neural Networks","created":"2021-09-29","cited_by_count":6,"area":null},{"id":"2207.00411","title":"Adversarial Robustness is at Odds with Lazy Training","created":"2022-06-18","cited_by_count":6,"area":null},{"id":"2203.08961","title":"On the Convergence of Certified Robust Training with Interval Bound Propagation","created":"2022-03-16","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":"2301.08117","title":"Convergence beyond the over-parameterized regime using Rayleigh quotients","created":"2023-01-19","cited_by_count":5,"area":null},{"id":"2406.03944","title":"Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples","created":"2024-06-06","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":"2111.14039","title":"Generalization Performance of Empirical Risk Minimization on Over-parameterized Deep ReLU Nets","created":"2021-11-28","cited_by_count":4,"area":null},{"id":"2205.05662","title":"Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis","created":"2022-05-11","cited_by_count":4,"area":null},{"id":"2503.09565","title":"Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $\\mu$P Parametrization","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2104.11895","title":"Achieving Small Test Error in Mildly Overparameterized Neural Networks","created":"2021-04-24","cited_by_count":3,"area":null},{"id":"2209.15265","title":"Overparameterized ReLU Neural Networks Learn the Simplest Models: Neural Isometry and Exact Recovery","created":"2022-09-30","cited_by_count":3,"area":null},{"id":"2210.16286","title":"A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks","created":"2022-10-28","cited_by_count":3,"area":null},{"id":"2301.00335","title":"Pruning Before Training May Improve Generalization, Provably","created":"2023-01-01","cited_by_count":3,"area":null},{"id":"2409.05349","title":"On the Convergence Analysis of Over-Parameterized Variational Autoencoders: A Neural Tangent Kernel Perspective","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2502.20681","title":"Disentangling Feature Structure: A Mathematically Provable Two-Stage Training Dynamics in Transformers","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2510.02779","title":"Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification","created":"2025-10-03","cited_by_count":3,"area":null},{"id":"2102.13522","title":"Experiments with Rich Regime Training for Deep Learning","created":"2021-02-26","cited_by_count":2,"area":null},{"id":"2206.07483","title":"Blind Estimation of a Doubly Selective OFDM Channel: A Deep Learning Algorithm and Theory","created":"2022-05-30","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":"2402.11942","title":"The effect of Leaky ReLUs on the training and generalization of overparameterized networks","created":"2024-02-19","cited_by_count":2,"area":null},{"id":"2201.06658","title":"Learning Neural Ranking Models Online from Implicit User Feedback","created":"2022-01-17","cited_by_count":1,"area":null},{"id":"2201.12052","title":"Improved Overparametrization Bounds for Global Convergence of Stochastic Gradient Descent for Shallow Neural Networks","created":"2022-01-28","cited_by_count":1,"area":null},{"id":"2212.02323","title":"Improved Convergence Guarantees for Shallow Neural Networks","created":"2022-12-05","cited_by_count":1,"area":null},{"id":"2306.07544","title":"On Achieving Optimal Adversarial Test Error","created":"2023-06-13","cited_by_count":1,"area":null},{"id":"2405.11451","title":"Error Analysis of Three-Layer Neural Network Trained with PGD for Deep Ritz Method","created":"2024-05-19","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":"2409.14174","title":"Component-based Sketching for Deep ReLU Nets","created":"2024-09-21","cited_by_count":1,"area":null},{"id":"2410.17128","title":"Understanding Transfer Learning via Mean-field Analysis","created":"2024-10-22","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":"2601.22409","title":"Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov-Arnold Networks","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2605.10775","title":"On the global convergence of gradient flow for wide shallow models beyond homogeneous nonlinearities","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2102.00853","title":"Painless step size adaptation for SGD","created":"2021-02-01","cited_by_count":0,"area":null},{"id":"2104.02578","title":"Neurons learn slower than they think","created":"2021-04-02","cited_by_count":0,"area":null},{"id":"2202.09276","title":"Geometric Regularization from Overparameterization","created":"2022-02-18","cited_by_count":0,"area":null},{"id":"2202.10670","title":"From Optimization Dynamics to Generalization Bounds via {\\L}ojasiewicz Gradient Inequality","created":"2022-02-22","cited_by_count":0,"area":null},{"id":"2207.00751","title":"Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity","created":"2022-07-02","cited_by_count":0,"area":null},{"id":"2309.06774","title":"Fundamental Limits of Deep Learning-Based Binary Classifiers Trained with Hinge Loss","created":"2023-09-13","cited_by_count":0,"area":null},{"id":"2501.05930","title":"Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2509.23887","title":"Gradient Flow Convergence Guarantee for General Neural Network Architectures","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2604.00505","title":"Towards Initialization-dependent and Non-vacuous Generalization Bounds for Overparameterized Shallow Neural Networks","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2606.06764","title":"Optimal Rates for Generalization of Gradient Descent Methods with Deep Neural Networks","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.30831","title":"Geometric Dyson Brownian Motions and the Free Log-Normal Limit for a Non-Square Gaussian Matrix Product","created":"2026-06-29","cited_by_count":0,"area":null}],"next_cursor":null}