{"total":19,"rows":[{"id":"2106.15002","title":"Characterization of the Variation Spaces Corresponding to Shallow Neural Networks","created":"2021-06-28","cited_by_count":48,"area":null},{"id":"2402.01258","title":"Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape","created":"2024-02-02","cited_by_count":46,"area":null},{"id":"2303.01353","title":"Penalising the biases in norm regularisation enforces sparsity","created":"2023-03-02","cited_by_count":19,"area":null},{"id":"2206.03299","title":"Generalization Error Bounds for Deep Neural Networks Trained by SGD","created":"2022-06-07","cited_by_count":14,"area":null},{"id":"2205.14421","title":"Approximation of Functionals by Neural Network without Curse of Dimensionality","created":"2022-05-28","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":"2312.08461","title":"Space-Time Approximation with Shallow Neural Networks in Fourier Lebesgue spaces","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2209.01173","title":"Optimal bump functions for shallow ReLU networks: Weight decay, depth separation and the curse of dimensionality","created":"2022-09-02","cited_by_count":4,"area":null},{"id":"2305.15839","title":"Embeddings between Barron spaces with higher order activation functions","created":"2023-05-25","cited_by_count":4,"area":null},{"id":"2311.06138","title":"Minimum norm interpolation by perceptra: Explicit regularization and implicit bias","created":"2023-11-10","cited_by_count":3,"area":null},{"id":"2303.08587","title":"Delay-SDE-net: A deep learning approach for time series modelling with memory and uncertainty estimates","created":"2023-03-14","cited_by_count":2,"area":null},{"id":"2305.19082","title":"Embedding Inequalities for Barron-type Spaces","created":"2023-05-30","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":"2412.07728","title":"Solving the Poisson Equation with Dirichlet data by shallow ReLU$^\\alpha$-networks: A regularity and approximation perspective","created":"2024-12-10","cited_by_count":2,"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":"2502.05360","title":"Curse of Dimensionality in Neural Network Optimization","created":"2025-02-07","cited_by_count":1,"area":null},{"id":"2509.23474","title":"Statistical Learning Guarantees for Group-Invariant Barron Functions","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2607.25100","title":"Elliptic Regularity Theory in Barron Spaces and Applications to the Deep Ritz Method","created":"2026-07-27","cited_by_count":1,"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}],"next_cursor":null}