{"total":21,"rows":[{"id":"2210.07082","title":"Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"2307.12851","title":"Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization","created":"2023-07-24","cited_by_count":28,"area":null},{"id":"2204.03497","title":"Generalised Latent Assimilation in Heterogeneous Reduced Spaces with Machine Learning Surrogate Models","created":"2022-04-07","cited_by_count":26,"area":null},{"id":"2305.05119","title":"Flexible Job Shop Scheduling via Dual Attention Network Based Reinforcement Learning","created":"2023-05-09","cited_by_count":20,"area":null},{"id":"2101.02533","title":"Towards Understanding Learning in Neural Networks with Linear Teachers","created":"2021-01-07","cited_by_count":19,"area":null},{"id":"2201.08514","title":"How does unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis","created":"2022-01-21","cited_by_count":19,"area":null},{"id":"2310.16173","title":"On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\\epsilon$-Greedy Exploration","created":"2023-10-24","cited_by_count":17,"area":null},{"id":"2107.04228","title":"Activated Gradients for Deep Neural Networks","created":"2021-07-09","cited_by_count":14,"area":null},{"id":"2310.16187","title":"Efficient deep data assimilation with sparse observations and time-varying sensors","created":"2023-10-24","cited_by_count":14,"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":"2206.09149","title":"Piecewise Linear Neural Networks and Deep Learning","created":"2022-06-18","cited_by_count":7,"area":null},{"id":"2306.09955","title":"Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign?","created":"2023-06-16","cited_by_count":7,"area":null},{"id":"2406.12615","title":"When Are Bias-Free ReLU Networks Effectively Linear Networks?","created":"2024-06-18","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":"2302.12261","title":"Testing Stationarity Concepts for ReLU Networks: Hardness, Regularity, and Robust Algorithms","created":"2023-02-23","cited_by_count":2,"area":null},{"id":"2203.14607","title":"Boosting Black-Box Adversarial Attacks with Meta Learning","created":"2022-03-28","cited_by_count":1,"area":null},{"id":"2310.01758","title":"Linearization of ReLU Activation Function for Neural Network-Embedded Optimization: Optimal Day-Ahead Energy Scheduling","created":"2023-10-03","cited_by_count":1,"area":null},{"id":"2508.09161","title":"Physics-Guided Memory Network for Building Energy Modeling","created":"2025-08-05","cited_by_count":1,"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":"2510.05888","title":"BioAutoML-NAS: An End-to-End AutoML Framework for Multimodal Insect Classification via Neural Architecture Search on Large-Scale Biodiversity Data","created":"2025-10-07","cited_by_count":0,"area":null}],"next_cursor":null}