| Benign, tempered, or catastrophic: A taxonomy of overfitting N Mallinar, JB Simon, A Abedsoltan, P Pandit, M Belkin, P Nakkiran 36th Conference on Neural Information Processing Systems (NeurIPS 2022), 2022 | 81* | 2022 |
| Toward Large Kernel Models A Abedsoltan, M Belkin, P Pandit 40th International Conference on Machine Learning (ICML2023), 2023 | 21 | 2023 |
| On the Nyström approximation for preconditioning in kernel machines A Abedsoltan, P Pandit, L Rademacher, M Belkin International Conference on Artificial Intelligence and Statistics, 3718-3726, 2024 | 4 | 2024 |
| Context-Scaling versus Task-Scaling in In-Context Learning A Abedsoltan, A Radhakrishnan, J Wu, M Belkin arXiv preprint arXiv:2410.12783, 2024 | 2 | 2024 |
| On emergence of clean-priority learning in early stopped neural networks C Liu, A Abedsoltan, M Belkin arXiv preprint arXiv:2306.02533, 2023 | 2 | 2023 |
| Task Generalization With AutoRegressive Compositional Structure: Can Learning From $\d $ Tasks Generalize to $\d^{T} $ Tasks? A Abedsoltan, H Zhang, K Wen, H Lin, J Zhang, M Belkin arXiv preprint arXiv:2502.08991, 2025 | | 2025 |
| Fast training of large kernel models with delayed projections A Abedsoltan, S Ma, P Pandit, M Belkin arXiv preprint arXiv:2411.16658, 2024 | | 2024 |
| Uncertainty estimation with recursive feature machines D Gedon, A Abedsoltan, TB Schön, M Belkin The 40th Conference on Uncertainty in Artificial Intelligence, 2024 | | 2024 |
| On Feature Learning of Recursive Feature Machines and Automatic Relevance Determination D Gedon, A Abedsoltan, TB Schön, M Belkin UniReps: the First Workshop on Unifying Representations in Neural Models, 0 | | |
Mikhail (Misha) BelkinProfessor of Data Science, Halıcıoğlu Data Science Institute, CSE, UCSD, Amazon ScholarVerifierad e-postadress på ucsd.edu