 Hamiltonian Monte Carlo on ReLU Neural Networks is InefficientNeural Information Processing Systems (NeurIPS), 2024 |
 Robust SDE-Based Variational Formulations for Solving Linear PDEs via
Deep LearningInternational Conference on Machine Learning (ICML), 2022 |
 How degenerate is the parametrization of neural networks with the ReLU
activation function?Neural Information Processing Systems (NeurIPS), 2019 |
