{"total":16,"rows":[{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288,"area":null},{"id":"2101.12176","title":"On the Origin of Implicit Regularization in Stochastic Gradient Descent","created":"2021-01-28","cited_by_count":184,"area":null},{"id":"2105.13343","title":"Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error","created":"2021-05-27","cited_by_count":33,"area":null},{"id":"2206.12543","title":"A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel","created":"2022-06-25","cited_by_count":30,"area":null},{"id":"2207.09405","title":"Bayesian Generational Population-Based Training","created":"2022-07-19","cited_by_count":20,"area":null},{"id":"2312.12226","title":"On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width","created":"2023-12-19","cited_by_count":15,"area":null},{"id":"2212.07295","title":"Maximal Initial Learning Rates in Deep ReLU Networks","created":"2022-12-14","cited_by_count":11,"area":null},{"id":"2410.05838","title":"Time Transfer: On Optimal Learning Rate and Batch Size In The Infinite Data Limit","created":"2024-10-08","cited_by_count":9,"area":null},{"id":"2310.07765","title":"Feature Learning and Generalization in Deep Networks with Orthogonal Weights","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2202.04509","title":"Optimal learning rate schedules in high-dimensional non-convex optimization problems","created":"2022-02-09","cited_by_count":4,"area":null},{"id":"2402.17440","title":"Principled Architecture-aware Scaling of Hyperparameters","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2412.01120","title":"Reliable and scalable variable importance estimation via warm-start and early stopping","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2501.09137","title":"Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks","created":"2025-01-15","cited_by_count":2,"area":null},{"id":"2508.12576","title":"Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2407.18807","title":"When narrower is better: the narrow width limit of Bayesian parallel branching neural networks","created":"2024-07-26","cited_by_count":1,"area":null},{"id":"2303.09216","title":"Controlled Descent Training","created":"2023-03-16","cited_by_count":0,"area":null}],"next_cursor":null}