| Pulse: Self-supervised photo upsampling via latent space exploration of generative models S Menon, A Damian, S Hu, N Ravi, C Rudin Proceedings of the ieee/cvf conference on computer vision and pattern …, 2020 | 530 | 2020 |
| Label noise sgd provably prefers flat global minimizers A Damian, T Ma, JD Lee Advances in Neural Information Processing Systems 34, 27449-27461, 2021 | 100 | 2021 |
| Neural networks can learn representations with gradient descent A Damian, J Lee, M Soltanolkotabi Conference on Learning Theory, 5413-5452, 2022 | 84 | 2022 |
| Fine-tuning language models with just forward passes S Malladi, T Gao, E Nichani, A Damian, JD Lee, D Chen, S Arora Advances in Neural Information Processing Systems 36, 2024 | 61 | 2024 |
| Self-stabilization: The implicit bias of gradient descent at the edge of stability A Damian, E Nichani, JD Lee arXiv preprint arXiv:2209.15594, 2022 | 55 | 2022 |
| New techniques for preserving global structure and denoising with low information loss in single-image super-resolution Y Bei, A Damian, S Hu, S Menon, N Ravi, C Rudin Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2018 | 35 | 2018 |
| Smoothing the landscape boosts the signal for sgd: Optimal sample complexity for learning single index models A Damian, E Nichani, R Ge, JD Lee Advances in Neural Information Processing Systems 36, 2024 | 11 | 2024 |
| Provable guarantees for nonlinear feature learning in three-layer neural networks E Nichani, A Damian, JD Lee Advances in Neural Information Processing Systems 36, 2024 | 4 | 2024 |
| How Transformers Learn Causal Structure with Gradient Descent E Nichani, A Damian, JD Lee arXiv preprint arXiv:2402.14735, 2024 | 3 | 2024 |
| The Computational Complexity of Learning Gaussian Single-Index Models A Damian, L Pillaud-Vivien, JD Lee, J Bruna arXiv preprint arXiv:2403.05529, 2024 | 1 | 2024 |
| Squeeze-Free Hamiltonian Paths in Grid Graphs A Damian, R Flatland Conference on Computational Geometry, 241, 2015 | | 2015 |
