 On the generalization of learning algorithms that do not convergeNeural Information Processing Systems (NeurIPS), 2022 |
 Understanding the Generalization Benefit of Normalization Layers:
Sharpness ReductionNeural Information Processing Systems (NeurIPS), 2022 |
 Chaotic Regularization and Heavy-Tailed Limits for Deterministic
Gradient DescentNeural Information Processing Systems (NeurIPS), 2022 |
 Beyond the Quadratic Approximation: the Multiscale Structure of Neural
Network Loss LandscapesJournal of Machine Learning (JML), 2022 |
 A novel multi-scale loss function for classification problems in machine
learningJournal of Computational Physics (JCP), 2021 |
