Neural Networks Efficiently Learn Low-Dimensional Representations with SGD A Mousavi-Hosseini, S Park, M Girotti, I Mitliagkas, MA Erdogdu International Conference on Learning Representations 2023, 2022 | 44 | 2022 |
Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincar\'e Inequality A Mousavi-Hosseini, T Farghly, Y He, K Balasubramanian, MA Erdogdu The Thirty Sixth Annual Conference on Learning Theory, 1-35, 2023 | 17 | 2023 |
Gradient-Based Feature Learning under Structured Data A Mousavi-Hosseini, D Wu, T Suzuki, MA Erdogdu Thirty-seventh Conference on Neural Information Processing Systems, 2023 | 16 | 2023 |
The interplay between distribution parameters and the accuracy-robustness tradeoff in classification AM Hosseini, AM Abouei, MH Rohban arXiv preprint arXiv:2107.00247, 2021 | 1 | 2021 |
Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach G Wang, A Mousavi-Hosseini, L Chizat arXiv preprint arXiv:2406.17054, 2024 | | 2024 |
A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers Y He, A Mousavi-Hosseini, K Balasubramanian, MA Erdogdu arXiv preprint arXiv:2405.16736, 2024 | | 2024 |