 TRAM: Bridging Trust Regions and Sharpness Aware MinimizationInternational Conference on Learning Representations (ICLR), 2023 |
 Plateau in Monotonic Linear Interpolation -- A "Biased" View of Loss
Landscape for Deep NetworksInternational Conference on Learning Representations (ICLR), 2022 |
 Git Re-Basin: Merging Models modulo Permutation SymmetriesInternational Conference on Learning Representations (ICLR), 2022 |
 When Do Flat Minima Optimizers Work?Neural Information Processing Systems (NeurIPS), 2022 |
 What can linear interpolation of neural network loss landscapes tell us?International Conference on Machine Learning (ICML), 2021 |
 Personalized Algorithm Generation: A Case Study in Learning ODE
IntegratorsSIAM Journal on Scientific Computing (SISC), 2021 |
 Learning Neural Network SubspacesInternational Conference on Machine Learning (ICML), 2021 |
